Maintained by Difan Deng and Marius Lindauer.
The following list considers papers related to neural architecture search. It is by no means complete. If you miss a paper on the list, please let us know.
Please note that although NAS methods steadily improve, the quality of empirical evaluations in this field are still lagging behind compared to other areas in machine learning, AI and optimization. We would therefore like to share some best practices for empirical evaluations of NAS methods, which we believe will facilitate sustained and measurable progress in the field. If you are interested in a teaser, please read our blog post or directly jump to our checklist.
Transformers have gained increasing popularity in different domains. For a comprehensive list of papers focusing on Neural Architecture Search for Transformer-Based spaces, the awesome-transformer-search repo is all you need.
5555
4236.
Zhu, Huijuan; Xia, Mengzhen; Wang, Liangmin; Xu, Zhicheng; Sheng, Victor S.
A Novel Knowledge Search Structure for Android Malware Detection Journal Article
In: IEEE Transactions on Services Computing, no. 01, pp. 1-14, 5555, ISSN: 1939-1374.
@article{10750332,
title = { A Novel Knowledge Search Structure for Android Malware Detection },
author = {Huijuan Zhu and Mengzhen Xia and Liangmin Wang and Zhicheng Xu and Victor S. Sheng},
url = {https://doi.ieeecomputersociety.org/10.1109/TSC.2024.3496333},
doi = {10.1109/TSC.2024.3496333},
issn = {1939-1374},
year = {5555},
date = {5555-11-01},
urldate = {5555-11-01},
journal = {IEEE Transactions on Services Computing},
number = {01},
pages = {1-14},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {While the Android platform is gaining explosive popularity, the number of malicious software (malware) is also increasing sharply. Thus, numerous malware detection schemes based on deep learning have been proposed. However, they are usually suffering from the cumbersome models with complex architectures and tremendous parameters. They usually require heavy computation power support, which seriously limit their deployment on actual application environments with limited resources (e.g., mobile edge devices). To surmount this challenge, we propose a novel Knowledge Distillation (KD) structure—Knowledge Search (KS). KS exploits Neural Architecture Search (NAS) to adaptively bridge the capability gap between teacher and student networks in KD by introducing a parallelized student-wise search approach. In addition, we carefully analyze the characteristics of malware and locate three cost-effective types of features closely related to malicious attacks, namely, Application Programming Interfaces (APIs), permissions and vulnerable components, to characterize Android Applications (Apps). Therefore, based on typical samples collected in recent years, we refine features while exploiting the natural relationship between them, and construct corresponding datasets. Massive experiments are conducted to investigate the effectiveness and sustainability of KS on these datasets. Our experimental results show that the proposed method yields an accuracy of 97.89% to detect Android malware, which performs better than state-of-the-art solutions.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
While the Android platform is gaining explosive popularity, the number of malicious software (malware) is also increasing sharply. Thus, numerous malware detection schemes based on deep learning have been proposed. However, they are usually suffering from the cumbersome models with complex architectures and tremendous parameters. They usually require heavy computation power support, which seriously limit their deployment on actual application environments with limited resources (e.g., mobile edge devices). To surmount this challenge, we propose a novel Knowledge Distillation (KD) structure—Knowledge Search (KS). KS exploits Neural Architecture Search (NAS) to adaptively bridge the capability gap between teacher and student networks in KD by introducing a parallelized student-wise search approach. In addition, we carefully analyze the characteristics of malware and locate three cost-effective types of features closely related to malicious attacks, namely, Application Programming Interfaces (APIs), permissions and vulnerable components, to characterize Android Applications (Apps). Therefore, based on typical samples collected in recent years, we refine features while exploiting the natural relationship between them, and construct corresponding datasets. Massive experiments are conducted to investigate the effectiveness and sustainability of KS on these datasets. Our experimental results show that the proposed method yields an accuracy of 97.89% to detect Android malware, which performs better than state-of-the-art solutions.
4235.
Zhang, Feifei; Li, Mao; Ge, Jidong; Tang, Fenghui; Zhang, Sheng; Wu, Jie; Luo, Bin
Privacy-Preserving Federated Neural Architecture Search With Enhanced Robustness for Edge Computing Journal Article
In: IEEE Transactions on Mobile Computing, no. 01, pp. 1-18, 5555, ISSN: 1558-0660.
@article{10742476,
title = { Privacy-Preserving Federated Neural Architecture Search With Enhanced Robustness for Edge Computing },
author = {Feifei Zhang and Mao Li and Jidong Ge and Fenghui Tang and Sheng Zhang and Jie Wu and Bin Luo},
url = {https://doi.ieeecomputersociety.org/10.1109/TMC.2024.3490835},
doi = {10.1109/TMC.2024.3490835},
issn = {1558-0660},
year = {5555},
date = {5555-11-01},
urldate = {5555-11-01},
journal = {IEEE Transactions on Mobile Computing},
number = {01},
pages = {1-18},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {With the development of large-scale artificial intelligence services, edge devices are becoming essential providers of data and computing power. However, these edge devices are not immune to malicious attacks. Federated learning (FL), while protecting privacy of decentralized data through secure aggregation, struggles to trace adversaries and lacks optimization for heterogeneity. We discover that FL augmented with Differentiable Architecture Search (DARTS) can improve resilience against backdoor attacks while compatible with secure aggregation. Based on this, we propose a federated neural architecture search (NAS) framwork named SLNAS. The architecture of SLNAS is built on three pivotal components: a server-side search space generation method that employs an evolutionary algorithm with dual encodings, a federated NAS process based on DARTS, and client-side architecture tuning that utilizes Gumbel softmax combined with knowledge distillation. To validate robustness, we adapt a framework that includes backdoor attacks based on trigger optimization, data poisoning, and model poisoning, targeting both model weights and architecture parameters. Extensive experiments demonstrate that SLNAS not only effectively counters advanced backdoor attacks but also handles heterogeneity, outperforming defense baselines across a wide range of backdoor attack scenarios.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
With the development of large-scale artificial intelligence services, edge devices are becoming essential providers of data and computing power. However, these edge devices are not immune to malicious attacks. Federated learning (FL), while protecting privacy of decentralized data through secure aggregation, struggles to trace adversaries and lacks optimization for heterogeneity. We discover that FL augmented with Differentiable Architecture Search (DARTS) can improve resilience against backdoor attacks while compatible with secure aggregation. Based on this, we propose a federated neural architecture search (NAS) framwork named SLNAS. The architecture of SLNAS is built on three pivotal components: a server-side search space generation method that employs an evolutionary algorithm with dual encodings, a federated NAS process based on DARTS, and client-side architecture tuning that utilizes Gumbel softmax combined with knowledge distillation. To validate robustness, we adapt a framework that includes backdoor attacks based on trigger optimization, data poisoning, and model poisoning, targeting both model weights and architecture parameters. Extensive experiments demonstrate that SLNAS not only effectively counters advanced backdoor attacks but also handles heterogeneity, outperforming defense baselines across a wide range of backdoor attack scenarios.
4234.
Zhang, Yu-Ming; Hsieh, Jun-Wei; Lee, Chun-Chieh; Fan, Kuo-Chin
RATs-NAS: Redirection of Adjacent Trails on Graph Convolutional Networks for Predictor-based Neural Architecture Search Journal Article
In: IEEE Transactions on Artificial Intelligence, vol. 1, no. 01, pp. 1-11, 5555, ISSN: 2691-4581.
@article{10685480,
title = { RATs-NAS: Redirection of Adjacent Trails on Graph Convolutional Networks for Predictor-based Neural Architecture Search },
author = {Yu-Ming Zhang and Jun-Wei Hsieh and Chun-Chieh Lee and Kuo-Chin Fan},
url = {https://doi.ieeecomputersociety.org/10.1109/TAI.2024.3465433},
doi = {10.1109/TAI.2024.3465433},
issn = {2691-4581},
year = {5555},
date = {5555-09-01},
urldate = {5555-09-01},
journal = {IEEE Transactions on Artificial Intelligence},
volume = {1},
number = {01},
pages = {1-11},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {Manually designed CNN architectures like VGG, ResNet, DenseNet, and MobileNet have achieved high performance across various tasks, but design them is time-consuming and costly. Neural Architecture Search (NAS) automates the discovery of effective CNN architectures, reducing the need for experts. However, evaluating candidate architectures requires significant GPU resources, leading to the use of predictor-based NAS, such as graph convolutional networks (GCN), which is the popular option to construct predictors. However, we discover that, even though the ability of GCN mimics the propagation of features of real architectures, the binary nature of the adjacency matrix limits its effectiveness. To address this, we propose Redirection of Adjacent Trails (RATs), which adaptively learns trail weights within the adjacency matrix. Our RATs-GCN outperform other predictors by dynamically adjusting trail weights after each graph convolution layer. Additionally, the proposed Divide Search Sampling (DSS) strategy, based on the observation of cell-based NAS that architectures with similar FLOPs perform similarly, enhances search efficiency. Our RATs-NAS, which combine RATs-GCN and DSS, shows significant improvements over other predictor-based NAS methods on NASBench-101, NASBench-201, and NASBench-301.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Manually designed CNN architectures like VGG, ResNet, DenseNet, and MobileNet have achieved high performance across various tasks, but design them is time-consuming and costly. Neural Architecture Search (NAS) automates the discovery of effective CNN architectures, reducing the need for experts. However, evaluating candidate architectures requires significant GPU resources, leading to the use of predictor-based NAS, such as graph convolutional networks (GCN), which is the popular option to construct predictors. However, we discover that, even though the ability of GCN mimics the propagation of features of real architectures, the binary nature of the adjacency matrix limits its effectiveness. To address this, we propose Redirection of Adjacent Trails (RATs), which adaptively learns trail weights within the adjacency matrix. Our RATs-GCN outperform other predictors by dynamically adjusting trail weights after each graph convolution layer. Additionally, the proposed Divide Search Sampling (DSS) strategy, based on the observation of cell-based NAS that architectures with similar FLOPs perform similarly, enhances search efficiency. Our RATs-NAS, which combine RATs-GCN and DSS, shows significant improvements over other predictor-based NAS methods on NASBench-101, NASBench-201, and NASBench-301.
4233.
Chen, X.; Yang, C.
CIMNet: Joint Search for Neural Network and Computing-in-Memory Architecture Journal Article
In: IEEE Micro, no. 01, pp. 1-12, 5555, ISSN: 1937-4143.
@article{10551739,
title = {CIMNet: Joint Search for Neural Network and Computing-in-Memory Architecture},
author = {X. Chen and C. Yang},
url = {https://www.computer.org/csdl/magazine/mi/5555/01/10551739/1XyKBmSlmPm},
doi = {10.1109/MM.2024.3409068},
issn = {1937-4143},
year = {5555},
date = {5555-06-01},
urldate = {5555-06-01},
journal = {IEEE Micro},
number = {01},
pages = {1-12},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {Computing-in-memory (CIM) architecture has been proven to effectively transcend the memory wall bottleneck, expanding the potential of low-power and high-throughput applications such as machine learning. Neural architecture search (NAS) designs ML models to meet a variety of accuracy, latency, and energy constraints. However, integrating CIM into NAS presents a major challenge due to additional simulation overhead from the non-ideal characteristics of CIM hardware. This work introduces a quantization and device aware accuracy predictor that jointly scores quantization policy, CIM architecture, and neural network architecture, eliminating the need for time-consuming simulations in the search process. We also propose reducing the search space based on architectural observations, resulting in a well-pruned search space customized for CIM. These allow for efficient exploration of superior combinations in mere CPU minutes. Our methodology yields CIMNet, which consistently improves the trade-off between accuracy and hardware efficiency on benchmarks, providing valuable architectural insights.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Computing-in-memory (CIM) architecture has been proven to effectively transcend the memory wall bottleneck, expanding the potential of low-power and high-throughput applications such as machine learning. Neural architecture search (NAS) designs ML models to meet a variety of accuracy, latency, and energy constraints. However, integrating CIM into NAS presents a major challenge due to additional simulation overhead from the non-ideal characteristics of CIM hardware. This work introduces a quantization and device aware accuracy predictor that jointly scores quantization policy, CIM architecture, and neural network architecture, eliminating the need for time-consuming simulations in the search process. We also propose reducing the search space based on architectural observations, resulting in a well-pruned search space customized for CIM. These allow for efficient exploration of superior combinations in mere CPU minutes. Our methodology yields CIMNet, which consistently improves the trade-off between accuracy and hardware efficiency on benchmarks, providing valuable architectural insights.
4232.
Lv, Hao; Zhang, Lei; Wang, Ying
In-situ NAS: A Plug-and-Search Neural Architecture Search framework across hardware platforms Journal Article
In: IEEE Transactions on Computers, no. 01, pp. 1-14, 5555, ISSN: 1557-9956.
@article{11003207,
title = { In-situ NAS: A Plug-and-Search Neural Architecture Search framework across hardware platforms },
author = {Hao Lv and Lei Zhang and Ying Wang},
url = {https://doi.ieeecomputersociety.org/10.1109/TC.2025.3569161},
doi = {10.1109/TC.2025.3569161},
issn = {1557-9956},
year = {5555},
date = {5555-05-01},
urldate = {5555-05-01},
journal = {IEEE Transactions on Computers},
number = {01},
pages = {1-14},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {Hardware-aware Neural Architecture Search (HW-NAS) has garnered significant research interest due to its ability to automate the design of neural networks for various hardware platforms. Prevalent HW-NAS frameworks often use fast predictors to estimate network performance, bypassing the time-consuming actual profiling step. However, the resource-intensive nature of building these predictors and their accuracy limitations hinder their practical use in diverse deployment scenarios. In response, we emphasize the indispensable role of actual profiling in HW-NAS and explore efficiency optimization possibilities within the HW-NAS framework. We provide a systematic analysis of profiling overhead in HW-NAS and identify many redundant and unnecessary operations during the search phase. We then optimize the workflow and present Insitu NAS, which leverages similarity features and exploration history to eliminate redundancy and improve runtime efficiency. In-situ NAS also offers simplified interfaces to ease the user’s effort in managing the complex device-dependent profiling flow, enabling plug-and-search functionality across diverse hardware platforms. Experimental results show that In-situ NAS achieves an average 10x speedup across different hardware platforms while reducing the search overhead by 8x compared to predictor-based approaches in various deployment scenarios. Additionally, In-situ NAS consistently discovers networks with better accuracy (about 1.5%) across diverse hardware platforms compared to predictor-based NAS.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Hardware-aware Neural Architecture Search (HW-NAS) has garnered significant research interest due to its ability to automate the design of neural networks for various hardware platforms. Prevalent HW-NAS frameworks often use fast predictors to estimate network performance, bypassing the time-consuming actual profiling step. However, the resource-intensive nature of building these predictors and their accuracy limitations hinder their practical use in diverse deployment scenarios. In response, we emphasize the indispensable role of actual profiling in HW-NAS and explore efficiency optimization possibilities within the HW-NAS framework. We provide a systematic analysis of profiling overhead in HW-NAS and identify many redundant and unnecessary operations during the search phase. We then optimize the workflow and present Insitu NAS, which leverages similarity features and exploration history to eliminate redundancy and improve runtime efficiency. In-situ NAS also offers simplified interfaces to ease the user’s effort in managing the complex device-dependent profiling flow, enabling plug-and-search functionality across diverse hardware platforms. Experimental results show that In-situ NAS achieves an average 10x speedup across different hardware platforms while reducing the search overhead by 8x compared to predictor-based approaches in various deployment scenarios. Additionally, In-situ NAS consistently discovers networks with better accuracy (about 1.5%) across diverse hardware platforms compared to predictor-based NAS.
4231.
Siddique, Ayesha; Hoque, Khaza Anuarul
Explainable AI-Guided Neural Architecture Search for Adversarial Robustness in Approximate DNNs Journal Article
In: IEEE Transactions on Sustainable Computing, no. 01, pp. 1-15, 5555, ISSN: 2377-3782.
@article{10966055,
title = { Explainable AI-Guided Neural Architecture Search for Adversarial Robustness in Approximate DNNs },
author = {Ayesha Siddique and Khaza Anuarul Hoque},
url = {https://doi.ieeecomputersociety.org/10.1109/TSUSC.2025.3561603},
doi = {10.1109/TSUSC.2025.3561603},
issn = {2377-3782},
year = {5555},
date = {5555-04-01},
urldate = {5555-04-01},
journal = {IEEE Transactions on Sustainable Computing},
number = {01},
pages = {1-15},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {Deep neural networks are lucrative targets of adversarial attacks and approximate deep neural networks (AxDNNs) are no exception. Searching manually for adversarially robust AxDNN architectures incurs outrageous time and human effort. In this paper, we propose XAI-NAS, an explainable neural architecture search (NAS) method that leverages explainable artificial intelligence (XAI) to efficiently co-optimize the adversarial robustness and hardware efficiency of AxDNN architectures on systolic-array hardware accelerators. During the NAS process, AxDNN architectures are evolved layer-wise with heterogeneous approximate multipliers to deliver the best trade-offs between adversarial robustness, energy consumption, latency, and memory footprint. The most suitable approximate multipliers are automatically selected from an open-source Evoapprox8b library. Our extensive evaluations provide a set of Pareto optimal hardware efficient and adversarially robust solutions. For example, a Pareto-optimal DNN AxDNN for the MNIST and CIFAR-10 datasets exhibits up to 1.5× higher adversarial robustness, 2.1× less energy consumption, 4.39× reduced latency, and 2.37× low memory footprint when compared to the state-of-the-art NAS approaches.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Deep neural networks are lucrative targets of adversarial attacks and approximate deep neural networks (AxDNNs) are no exception. Searching manually for adversarially robust AxDNN architectures incurs outrageous time and human effort. In this paper, we propose XAI-NAS, an explainable neural architecture search (NAS) method that leverages explainable artificial intelligence (XAI) to efficiently co-optimize the adversarial robustness and hardware efficiency of AxDNN architectures on systolic-array hardware accelerators. During the NAS process, AxDNN architectures are evolved layer-wise with heterogeneous approximate multipliers to deliver the best trade-offs between adversarial robustness, energy consumption, latency, and memory footprint. The most suitable approximate multipliers are automatically selected from an open-source Evoapprox8b library. Our extensive evaluations provide a set of Pareto optimal hardware efficient and adversarially robust solutions. For example, a Pareto-optimal DNN AxDNN for the MNIST and CIFAR-10 datasets exhibits up to 1.5× higher adversarial robustness, 2.1× less energy consumption, 4.39× reduced latency, and 2.37× low memory footprint when compared to the state-of-the-art NAS approaches.
4230.
Dong, Yukang; Pan, Fanxing; Gui, Yi; Jiang, Wenbin; Wan, Yao; Zheng, Ran; Jin, Hai
Comprehensive Architecture Search for Deep Graph Neural Networks Journal Article
In: IEEE Transactions on Big Data, no. 01, pp. 1-15, 5555, ISSN: 2332-7790.
@article{10930718,
title = { Comprehensive Architecture Search for Deep Graph Neural Networks },
author = {Yukang Dong and Fanxing Pan and Yi Gui and Wenbin Jiang and Yao Wan and Ran Zheng and Hai Jin},
url = {https://doi.ieeecomputersociety.org/10.1109/TBDATA.2025.3552336},
doi = {10.1109/TBDATA.2025.3552336},
issn = {2332-7790},
year = {5555},
date = {5555-03-01},
urldate = {5555-03-01},
journal = {IEEE Transactions on Big Data},
number = {01},
pages = {1-15},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {In recent years, Neural Architecture Search (NAS) has emerged as a promising approach for automatically discovering superior model architectures for deep Graph Neural Networks (GNNs). Different methods have paid attention to different types of search spaces. However, due to the time-consuming nature of training deep GNNs, existing NAS methods often fail to explore diverse search spaces sufficiently, which constrains their effectiveness. To crack this hard nut, we propose CAS-DGNN, a novel comprehensive architecture search method for deep GNNs. It encompasses four kinds of search spaces that are the composition of aggregate and update operators, different types of aggregate operators, residual connections, and hyper-parameters. To meet the needs of such a complex situation, a phased and hybrid search strategy is proposed to accommodate the diverse characteristics of different search spaces. Specifically, we divide the search process into four phases, utilizing evolutionary algorithms and Bayesian optimization. Meanwhile, we design two distinct search methods for residual connections (All-connected search and Initial Residual search) to streamline the search space, which enhances the scalability of CAS-DGNN. The experimental results show that CAS-DGNN achieves higher accuracy with competitive search costs across ten public datasets compared to existing methods.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In recent years, Neural Architecture Search (NAS) has emerged as a promising approach for automatically discovering superior model architectures for deep Graph Neural Networks (GNNs). Different methods have paid attention to different types of search spaces. However, due to the time-consuming nature of training deep GNNs, existing NAS methods often fail to explore diverse search spaces sufficiently, which constrains their effectiveness. To crack this hard nut, we propose CAS-DGNN, a novel comprehensive architecture search method for deep GNNs. It encompasses four kinds of search spaces that are the composition of aggregate and update operators, different types of aggregate operators, residual connections, and hyper-parameters. To meet the needs of such a complex situation, a phased and hybrid search strategy is proposed to accommodate the diverse characteristics of different search spaces. Specifically, we divide the search process into four phases, utilizing evolutionary algorithms and Bayesian optimization. Meanwhile, we design two distinct search methods for residual connections (All-connected search and Initial Residual search) to streamline the search space, which enhances the scalability of CAS-DGNN. The experimental results show that CAS-DGNN achieves higher accuracy with competitive search costs across ten public datasets compared to existing methods.
4229.
Yan, J.; Liu, J.; Xu, H.; Wang, Z.; Qiao, C.
Peaches: Personalized Federated Learning with Neural Architecture Search in Edge Computing Journal Article
In: IEEE Transactions on Mobile Computing, no. 01, pp. 1-17, 5555, ISSN: 1558-0660.
@article{10460163,
title = {Peaches: Personalized Federated Learning with Neural Architecture Search in Edge Computing},
author = {J. Yan and J. Liu and H. Xu and Z. Wang and C. Qiao},
doi = {10.1109/TMC.2024.3373506},
issn = {1558-0660},
year = {5555},
date = {5555-03-01},
urldate = {5555-03-01},
journal = {IEEE Transactions on Mobile Computing},
number = {01},
pages = {1-17},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {In edge computing (EC), federated learning (FL) enables numerous distributed devices (or workers) to collaboratively train AI models without exposing their local data. Most works of FL adopt a predefined architecture on all participating workers for model training. However, since workers' local data distributions vary heavily in EC, the predefined architecture may not be the optimal choice for every worker. It is also unrealistic to manually design a high-performance architecture for each worker, which requires intense human expertise and effort. In order to tackle this challenge, neural architecture search (NAS) has been applied in FL to automate the architecture design process. Unfortunately, the existing federated NAS frameworks often suffer from the difficulties of system heterogeneity and resource limitation. To remedy this problem, we present a novel framework, termed Peaches, to achieve efficient searching and training in the resource-constrained EC system. Specifically, the local model of each worker is stacked by base cell and personal cell, where the base cell is shared by all workers to capture the common knowledge and the personal cell is customized for each worker to fit the local data. We determine the number of base cells, shared by all workers, according to the bandwidth budget on the parameters server. Besides, to relieve the data and system heterogeneity, we find the optimal number of personal cells for each worker based on its computing capability. In addition, we gradually prune the search space during training to mitigate the resource consumption. We evaluate the performance of Peaches through extensive experiments, and the results show that Peaches can achieve an average accuracy improvement of about 6.29% and up to 3.97× speed up compared with the baselines.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In edge computing (EC), federated learning (FL) enables numerous distributed devices (or workers) to collaboratively train AI models without exposing their local data. Most works of FL adopt a predefined architecture on all participating workers for model training. However, since workers' local data distributions vary heavily in EC, the predefined architecture may not be the optimal choice for every worker. It is also unrealistic to manually design a high-performance architecture for each worker, which requires intense human expertise and effort. In order to tackle this challenge, neural architecture search (NAS) has been applied in FL to automate the architecture design process. Unfortunately, the existing federated NAS frameworks often suffer from the difficulties of system heterogeneity and resource limitation. To remedy this problem, we present a novel framework, termed Peaches, to achieve efficient searching and training in the resource-constrained EC system. Specifically, the local model of each worker is stacked by base cell and personal cell, where the base cell is shared by all workers to capture the common knowledge and the personal cell is customized for each worker to fit the local data. We determine the number of base cells, shared by all workers, according to the bandwidth budget on the parameters server. Besides, to relieve the data and system heterogeneity, we find the optimal number of personal cells for each worker based on its computing capability. In addition, we gradually prune the search space during training to mitigate the resource consumption. We evaluate the performance of Peaches through extensive experiments, and the results show that Peaches can achieve an average accuracy improvement of about 6.29% and up to 3.97× speed up compared with the baselines.
4228.
Sun, Genchen; Liu, Zhengkun; Gan, Lin; Su, Hang; Li, Ting; Zhao, Wenfeng; Sun, Biao
SpikeNAS-Bench: Benchmarking NAS Algorithms for Spiking Neural Network Architecture Journal Article
In: IEEE Transactions on Artificial Intelligence, vol. 1, no. 01, pp. 1-12, 5555, ISSN: 2691-4581.
@article{10855683,
title = { SpikeNAS-Bench: Benchmarking NAS Algorithms for Spiking Neural Network Architecture },
author = {Genchen Sun and Zhengkun Liu and Lin Gan and Hang Su and Ting Li and Wenfeng Zhao and Biao Sun},
url = {https://doi.ieeecomputersociety.org/10.1109/TAI.2025.3534136},
doi = {10.1109/TAI.2025.3534136},
issn = {2691-4581},
year = {5555},
date = {5555-01-01},
urldate = {5555-01-01},
journal = {IEEE Transactions on Artificial Intelligence},
volume = {1},
number = {01},
pages = {1-12},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {In recent years, Neural Architecture Search (NAS) has marked significant advancements, yet its efficacy is marred by the dependence on substantial computational resources. To mitigate this, the development of NAS benchmarks has emerged, offering datasets that enumerate all potential network architectures and their performances within a predefined search space. Nonetheless, these benchmarks predominantly focus on convolutional architectures, which are criticized for their limited interpretability and suboptimal hardware efficiency. Recognizing the untapped potential of Spiking Neural Networks (SNNs) — often hailed as the third generation of neural networks for their biological realism and computational thrift — this study introduces SpikeNAS-Bench. As a pioneering benchmark for SNN, SpikeNAS-Bench utilizes a cell-based search space, integrating leaky integrate-and-fire (LIF) neurons with variable thresholds as candidate operations. It encompasses 15,625 candidate architectures, rigorously evaluated on CIFAR10, CIFAR100 and Tiny-ImageNet datasets. This paper delves into the architectural nuances of SpikeNAS-Bench, leveraging various criteria to underscore the benchmark’s utility and presenting insights that could steer future NAS algorithm designs. Moreover, we assess the benchmark’s consistency through three distinct proxy types: zero-cost-based, early-stop-based, and predictor-based proxies. Additionally, the paper benchmarks seven contemporary NAS algorithms to attest to SpikeNAS-Bench’s broad applicability. We commit to providing training logs, diagnostic data for all candidate architectures, and the promise to release all code and datasets post-acceptance, aiming to catalyze further exploration and innovation within the SNN domain. SpikeNAS-Bench is open source at https://github.com/XXX (hidden for double anonymous review).},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In recent years, Neural Architecture Search (NAS) has marked significant advancements, yet its efficacy is marred by the dependence on substantial computational resources. To mitigate this, the development of NAS benchmarks has emerged, offering datasets that enumerate all potential network architectures and their performances within a predefined search space. Nonetheless, these benchmarks predominantly focus on convolutional architectures, which are criticized for their limited interpretability and suboptimal hardware efficiency. Recognizing the untapped potential of Spiking Neural Networks (SNNs) — often hailed as the third generation of neural networks for their biological realism and computational thrift — this study introduces SpikeNAS-Bench. As a pioneering benchmark for SNN, SpikeNAS-Bench utilizes a cell-based search space, integrating leaky integrate-and-fire (LIF) neurons with variable thresholds as candidate operations. It encompasses 15,625 candidate architectures, rigorously evaluated on CIFAR10, CIFAR100 and Tiny-ImageNet datasets. This paper delves into the architectural nuances of SpikeNAS-Bench, leveraging various criteria to underscore the benchmark’s utility and presenting insights that could steer future NAS algorithm designs. Moreover, we assess the benchmark’s consistency through three distinct proxy types: zero-cost-based, early-stop-based, and predictor-based proxies. Additionally, the paper benchmarks seven contemporary NAS algorithms to attest to SpikeNAS-Bench’s broad applicability. We commit to providing training logs, diagnostic data for all candidate architectures, and the promise to release all code and datasets post-acceptance, aiming to catalyze further exploration and innovation within the SNN domain. SpikeNAS-Bench is open source at https://github.com/XXX (hidden for double anonymous review).
4227.
Li, Changlin; Lin, Sihao; Tang, Tao; Wang, Guangrun; Li, Mingjie; Li, Zhihui; Chang, Xiaojun
BossNAS Family: Block-wisely Self-supervised Neural Architecture Search Journal Article
In: IEEE Transactions on Pattern Analysis & Machine Intelligence, no. 01, pp. 1-15, 5555, ISSN: 1939-3539.
@article{10839629,
title = { BossNAS Family: Block-wisely Self-supervised Neural Architecture Search },
author = {Changlin Li and Sihao Lin and Tao Tang and Guangrun Wang and Mingjie Li and Zhihui Li and Xiaojun Chang},
url = {https://doi.ieeecomputersociety.org/10.1109/TPAMI.2025.3529517},
doi = {10.1109/TPAMI.2025.3529517},
issn = {1939-3539},
year = {5555},
date = {5555-01-01},
urldate = {5555-01-01},
journal = {IEEE Transactions on Pattern Analysis & Machine Intelligence},
number = {01},
pages = {1-15},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {Recent advances in hand-crafted neural architectures for visual recognition underscore the pressing need to explore architecture designs comprising diverse building blocks. Concurrently, neural architecture search (NAS) methods have gained traction as a means to alleviate human efforts. Nevertheless, the question of whether NAS methods can efficiently and effectively manage diversified search spaces featuring disparate candidates, such as Convolutional Neural Networks (CNNs) and transformers, remains an open question. In this work, we introduce a novel unsupervised NAS approach called BossNAS (Block-wisely Self-supervised Neural Architecture Search), which aims to address the problem of inaccurate predictive architecture ranking caused by a large weight-sharing space while mitigating potential ranking issue caused by biased supervision. To achieve this, we factorize the search space into blocks and introduce a novel self-supervised training scheme called Ensemble Bootstrapping, to train each block separately in an unsupervised manner. In the search phase, we propose an unsupervised Population-Centric Search, optimizing the candidate architecture towards the population center. Additionally, we enhance our NAS method by integrating masked image modeling and present BossNAS++ to overcome the lack of dense supervision in our block-wise self-supervised NAS. In BossNAS++, we introduce the training technique named Masked Ensemble Bootstrapping for block-wise supernet, accompanied by a Masked Population-Centric Search scheme to promote fairer architecture selection. Our family of models, discovered through BossNAS and BossNAS++, delivers impressive results across various search spaces and datasets. Our transformer model discovered by BossNAS++ attains a remarkable accuracy of 83.2% on ImageNet with only 10.5B MAdds, surpassing DeiT-B by 1.4% while maintaining a lower computation cost. Moreover, our approach excels in architecture rating accuracy, achieving Spearman correlations of 0.78 and 0.76 on the canonical MBConv search space with ImageNet and the NATS-Bench size search space with CIFAR-100, respectively, outperforming state-of-the-art NAS methods.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Recent advances in hand-crafted neural architectures for visual recognition underscore the pressing need to explore architecture designs comprising diverse building blocks. Concurrently, neural architecture search (NAS) methods have gained traction as a means to alleviate human efforts. Nevertheless, the question of whether NAS methods can efficiently and effectively manage diversified search spaces featuring disparate candidates, such as Convolutional Neural Networks (CNNs) and transformers, remains an open question. In this work, we introduce a novel unsupervised NAS approach called BossNAS (Block-wisely Self-supervised Neural Architecture Search), which aims to address the problem of inaccurate predictive architecture ranking caused by a large weight-sharing space while mitigating potential ranking issue caused by biased supervision. To achieve this, we factorize the search space into blocks and introduce a novel self-supervised training scheme called Ensemble Bootstrapping, to train each block separately in an unsupervised manner. In the search phase, we propose an unsupervised Population-Centric Search, optimizing the candidate architecture towards the population center. Additionally, we enhance our NAS method by integrating masked image modeling and present BossNAS++ to overcome the lack of dense supervision in our block-wise self-supervised NAS. In BossNAS++, we introduce the training technique named Masked Ensemble Bootstrapping for block-wise supernet, accompanied by a Masked Population-Centric Search scheme to promote fairer architecture selection. Our family of models, discovered through BossNAS and BossNAS++, delivers impressive results across various search spaces and datasets. Our transformer model discovered by BossNAS++ attains a remarkable accuracy of 83.2% on ImageNet with only 10.5B MAdds, surpassing DeiT-B by 1.4% while maintaining a lower computation cost. Moreover, our approach excels in architecture rating accuracy, achieving Spearman correlations of 0.78 and 0.76 on the canonical MBConv search space with ImageNet and the NATS-Bench size search space with CIFAR-100, respectively, outperforming state-of-the-art NAS methods.
2026
4226.
Poyser, Matt; Breckon, Toby P.
DDS-NAS: Dynamic data selection within neural architecture search via on-line hard example mining applied to image classification Journal Article
In: Pattern Recognition, vol. 169, pp. 111948, 2026, ISSN: 0031-3203.
@article{POYSER2026111948,
title = {DDS-NAS: Dynamic data selection within neural architecture search via on-line hard example mining applied to image classification},
author = {Matt Poyser and Toby P. Breckon},
url = {https://www.sciencedirect.com/science/article/pii/S0031320325006089},
doi = {https://doi.org/10.1016/j.patcog.2025.111948},
issn = {0031-3203},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
journal = {Pattern Recognition},
volume = {169},
pages = {111948},
abstract = {In order to address the scalability challenge within Neural Architecture Search (NAS), we speed up NAS training via dynamic hard example mining within a curriculum learning framework. By utilising an autoencoder that enforces an image similarity embedding in latent space, we construct an efficient kd-tree structure to order images by furthest neighbour dissimilarity in a low-dimensional embedding. From a given query image from our subsample dataset, we can identify the most dissimilar image within the global dataset in logarithmic time. Via curriculum learning, we then dynamically re-formulate an unbiased subsample dataset for NAS optimisation, upon which the current NAS solution architecture performs poorly. We show that our DDS-NAS framework speeds up gradient-based NAS strategies by up to 27× without loss in performance. By maximising the contribution of each image sample during training, we reduce the duration of a NAS training cycle and the number of iterations required for convergence.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In order to address the scalability challenge within Neural Architecture Search (NAS), we speed up NAS training via dynamic hard example mining within a curriculum learning framework. By utilising an autoencoder that enforces an image similarity embedding in latent space, we construct an efficient kd-tree structure to order images by furthest neighbour dissimilarity in a low-dimensional embedding. From a given query image from our subsample dataset, we can identify the most dissimilar image within the global dataset in logarithmic time. Via curriculum learning, we then dynamically re-formulate an unbiased subsample dataset for NAS optimisation, upon which the current NAS solution architecture performs poorly. We show that our DDS-NAS framework speeds up gradient-based NAS strategies by up to 27× without loss in performance. By maximising the contribution of each image sample during training, we reduce the duration of a NAS training cycle and the number of iterations required for convergence.
2025
4225.
Wang, Weiqi; Bao, Feilong; Xing, Zhecong; Lian, Zhe
A Survey: Research Progress of Feature Fusion Technology Journal Article
In: 2025.
@article{wangsurvey,
title = {A Survey: Research Progress of Feature Fusion Technology},
author = {Weiqi Wang and Feilong Bao and Zhecong Xing and Zhe Lian},
url = {http://poster-openaccess.com/files/ICIC2024/862.pdf},
year = {2025},
date = {2025-12-01},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4224.
(Ed.)
MACHINE-GENERATED NEURAL NETWORKS FOR SHORT-TERM LOAD FORECASTING Collection
2025.
@collection{nokey,
title = { MACHINE-GENERATED NEURAL NETWORKS FOR SHORT-TERM LOAD FORECASTING},
author = {Gergana Vacheva and Plamen Stanchev and Nikolay Hinov
},
url = {https://unitechsp.tugab.bg/images/2024/1-EE/s1_p143_v1.pdf},
year = {2025},
date = {2025-12-01},
urldate = {2025-12-01},
booktitle = {International Scientific Conference UNITECH`2024},
journal = {International Scientific Conference UNITECH`2024},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
4223.
VOGGU, ARAVIND R.; R, KANISH; AKULA, NISHITH; MARUVADA, LOHITAKSH; SHIMIZU, TAKANORI; RAO, MADHAV
SIGNETS: Neural Network Architectures for m-QAM Soft Demodulation Journal Article
In: IEEE Access, 2025.
@article{nokey,
title = {SIGNETS: Neural Network Architectures for m-QAM Soft Demodulation},
author = {ARAVIND R. VOGGU and KANISH R and NISHITH AKULA and LOHITAKSH MARUVADA and TAKANORI SHIMIZU and MADHAV RAO },
url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=11071691},
year = {2025},
date = {2025-07-01},
urldate = {2025-07-01},
journal = {IEEE Access},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4222.
Song, Changwei; Ma, Yongjie
A Graph Generation Model for Convolutional Neural Network Architecture based on GCN and GAN Journal Article
In: Neural Processing Letters , 2025.
@article{nokey,
title = {A Graph Generation Model for Convolutional Neural Network Architecture based on GCN and GAN},
author = {Changwei Song and Yongjie Ma
},
url = {https://link.springer.com/article/10.1007/s11063-025-11773-7},
year = {2025},
date = {2025-07-01},
urldate = {2025-07-01},
journal = {Neural Processing Letters },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4221.
Liang, Jing; Liu, Genyue; Bi, Ying; Yu, Mingyuan; Liu, Mengnan; Jin, Yaochu
Evolutionary Neural Architecture Search for Remote Sensing Image Classification Journal Article
In: IEEE Trans Neural Netw Learn Syst . , 2025.
@article{liang-tnnls25a,
title = { Evolutionary Neural Architecture Search for Remote Sensing Image Classification },
author = {Jing Liang and Genyue Liu and Ying Bi and Mingyuan Yu and Mengnan Liu and Yaochu Jin
},
url = {https://pubmed.ncbi.nlm.nih.gov/40627480/},
year = {2025},
date = {2025-07-01},
urldate = {2025-07-01},
journal = { IEEE Trans Neural Netw Learn Syst . },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4220.
(Ed.)
Neural Architecture Search: Automation in Deep Learning Model Design Collection
2025.
@collection{nokey,
title = {Neural Architecture Search: Automation in Deep Learning Model Design},
author = {Manuel Egele},
url = {https://www.ijcnwc.com/admin/uploads/Neural%20Architecture%20Search%20Automation%20in%20Deep%20Learning%20Model%20Design.pdf},
year = {2025},
date = {2025-07-01},
urldate = {2025-07-01},
booktitle = {IRACST – International Journal of Computer Networks and Wireless Communications (IJCNWC)},
journal = {IRACST – International Journal of Computer Networks and Wireless Communications (IJCNWC)},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
4219.
Xiao, Siyang; Chen, Jiamin; Wu, Zhenpeng; Wu, Shuqing; Gao, Jianliang
DSA-GNAS: Graph Neural Architecture Search with Deep Semantic Adaption of Large Language Models Miscellaneous
2025.
@misc{nokey,
title = {DSA-GNAS: Graph Neural Architecture Search with Deep Semantic Adaption of Large Language Models},
author = {Siyang Xiao and Jiamin Chen and Zhenpeng Wu and Shuqing Wu and Jianliang Gao },
url = {https://www.researchsquare.com/article/rs-6639133/v1},
year = {2025},
date = {2025-06-30},
urldate = {2025-06-30},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
4218.
Liu, Ruyu; Wang, Lin; Yu, Zhihao; Zhang, Haoyu; Liu, Xiufeng; Sun, Bo; Huo, Xv; Zhang, Jianhua
SCTNet-NAS: efficient semantic segmentation via neural architecture search for cloud-edge collaborative perception Journal Article
In: Complex & Intelligent Systems , 2025.
@article{nokey,
title = {SCTNet-NAS: efficient semantic segmentation via neural architecture search for cloud-edge collaborative perception},
author = {
Ruyu Liu and Lin Wang and Zhihao Yu and Haoyu Zhang and Xiufeng Liu and Bo Sun and Xv Huo and Jianhua Zhang
},
url = {https://link.springer.com/article/10.1007/s40747-025-01996-5},
year = {2025},
date = {2025-06-30},
urldate = {2025-06-30},
journal = {Complex & Intelligent Systems },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4217.
Du, Boqian; Su, Sheng; Yu, Haijie; Wang, Yandong; Feng, Cuiying; Tian, Jing; Huang, Hongyu; Rajab, Ssemwogerere; Wang, Jingyi
A social development algorithm for neural architecture search Bachelor Thesis
2025.
@bachelorthesis{nokey,
title = {A social development algorithm for neural architecture search},
author = {Boqian Du and Sheng Su and Haijie Yu and Yandong Wang and Cuiying Feng and Jing Tian and Hongyu Huang and Ssemwogerere Rajab and Jingyi Wang
},
year = {2025},
date = {2025-06-06},
urldate = {2025-06-06},
keywords = {},
pubstate = {published},
tppubtype = {bachelorthesis}
}
4216.
Gupta, Ujjwal K.; Mishra, Shweta; Sharma, Shashikant A.
One day Ahead Forecasting of INSAT-3D Solar Irradiance Using Automated Deep ConvLSTM Network Journal Article
In: Journal of the Indian Society of Remote Sensing , 2025.
@article{nokey,
title = {One day Ahead Forecasting of INSAT-3D Solar Irradiance Using Automated Deep ConvLSTM Network},
author = {
Ujjwal K. Gupta and Shweta Mishra and Shashikant A. Sharma
},
url = {https://link.springer.com/article/10.1007/s12524-025-02258-0},
year = {2025},
date = {2025-06-01},
urldate = {2025-06-01},
journal = { Journal of the Indian Society of Remote Sensing },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4215.
Peng, Yang; Zhou, Shen Yao Huaichun; Chen, Yang; Zheng, Zhenyu; Gong, Xun
2025.
@misc{peng-25a,
title = {Online Quantitative Monitoring of Microalgae Concentration Using a Coupled Neural Network with Self-Search and Group Convolution},
author = {Yang Peng and Shen Yao Huaichun Zhou and Yang Chen and Zhenyu Zheng and Xun Gong},
url = {https://www.researchsquare.com/article/rs-6781945/v1},
year = {2025},
date = {2025-06-01},
urldate = {2025-06-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
4214.
(Ed.)
Prior Knowledge Guided Neural Architecture Generation Collection
2025.
@collection{Xie-ixml25a,
title = { Prior Knowledge Guided Neural Architecture Generation },
author = { Jingrong Xie and Han Ji and Yanan Sun },
url = {https://openreview.net/pdf?id=5QU8dAnLgO},
year = {2025},
date = {2025-06-01},
urldate = {2025-06-01},
booktitle = {ICML2025},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
4213.
Jeevidha, S.; Saraswathi, S.
In: Signal, Image and Video Processing , 2025.
@article{nokey,
title = {Implementation of vision transformer with adaptive neural architecture search for automated colon cancer classification through analysis of images},
author = {
S. Jeevidha and S. Saraswathi
},
url = {https://link.springer.com/article/10.1007/s11760-025-04193-6},
year = {2025},
date = {2025-06-01},
urldate = {2025-06-01},
journal = { Signal, Image and Video Processing },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4212.
(Ed.)
2025.
@collection{nokey,
title = { Improved search in graph AutoML: expansion and dynamic prioritization in the search space for enhanced efficiency },
author = { F. M. Balabanovab and K. S. Lukyanovcbd },
url = {https://www.mathnet.ru/php/archive.phtml?wshow=paper&jrnid=tisp&paperid=969&option_lang=eng},
year = {2025},
date = {2025-06-01},
urldate = {2025-06-01},
booktitle = {Proceedings of the Institute for System Programming of the RAS},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
4211.
Amjala, Shravan Kumar
Advancing Machine Learning Systems: A Comprehensive Analysis of Model Efficiency and Scalability Journal Article
In: Journal of Computer Science and Technology Studies, vol. 7, no. 6, pp. 679–683, 2025.
@article{ShravanKumarAmjala_2025,
title = {Advancing Machine Learning Systems: A Comprehensive Analysis of Model Efficiency and Scalability},
author = {Shravan Kumar Amjala},
url = {https://al-kindipublishers.org/index.php/jcsts/article/view/10060},
doi = {10.32996/jcsts.2025.7.79},
year = {2025},
date = {2025-06-01},
urldate = {2025-06-01},
journal = {Journal of Computer Science and Technology Studies},
volume = {7},
number = {6},
pages = {679–683},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4210.
Prete, Roberto Del; andAndrea Mazzeo, Parampuneet Kaur Thind; Whitley, Matthew; Papa, Lorenzo; Longepe, Nicolas; Meoni, Gabriele
Optimizing Deep Learning Models for On-Orbit Deployment Through Neural Architecture Search Miscellaneous
2025.
@misc{nokey,
title = {Optimizing Deep Learning Models for On-Orbit Deployment Through Neural Architecture Search},
author = {Roberto Del Prete and Parampuneet Kaur Thind andAndrea Mazzeo and Matthew Whitley and Lorenzo Papa and Nicolas Longepe and Gabriele Meoni},
url = {https://www.researchsquare.com/article/rs-6753230/v1},
year = {2025},
date = {2025-06-01},
urldate = {2025-06-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
4209.
Rex P. Flejoles, Joey S. Aviles
A Developed Tunable Model against Prebuild Applications to Classify Emotions Journal Article
In: International Journal of Science and Management Studies (IJSMS), vol. 8, iss. 3, 2025.
@article{nokey,
title = {A Developed Tunable Model against Prebuild Applications to Classify Emotions},
author = {Rex P. Flejoles, Joey S. Aviles},
url = {https://www.ijsmsjournal.org/ijsms-v8i3p110.html},
year = {2025},
date = {2025-06-01},
urldate = {2025-06-01},
journal = {International Journal of Science and Management Studies (IJSMS)},
volume = {8},
issue = {3},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4208.
David, Oluremi
Designing Lightweight Deep Neural Networks for Real- Time Bioinformatics Applications on Edge Devices Technical Report
2025.
@techreport{nokey,
title = {Designing Lightweight Deep Neural Networks for Real- Time Bioinformatics Applications on Edge Devices},
author = {Oluremi David},
url = {https://www.researchgate.net/profile/David-Oluremi/publication/392590151_Designing_Lightweight_Deep_Neural_Networks_for_Real-_Time_Bioinformatics_Applications_on_Edge_Devices/links/68498455514e67140ddefc1e/Designing-Lightweight-Deep-Neural-Networks-for-Real-Time-Bioinformatics-Applications-on-Edge-Devices.pdf},
year = {2025},
date = {2025-06-01},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
4207.
David, Oluremi
Joint Optimization of Neural Network Architecture and Inference Paths for Multi-Omics Data Integration Technical Report
2025.
@techreport{nokey,
title = {Joint Optimization of Neural Network Architecture and Inference Paths for Multi-Omics Data Integration},
author = {Oluremi David},
url = {https://www.researchgate.net/profile/David-Oluremi/publication/392590516_Joint_Optimization_of_Neural_Network_Architecture_and_Inference_Paths_for_Multi-Omics_Data_Integration/links/68498497dd8f4b7e2109b813/Joint-Optimization-of-Neural-Network-Architecture-and-Inference-Paths-for-Multi-Omics-Data-Integration.pdf},
year = {2025},
date = {2025-06-01},
urldate = {2025-06-01},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
4206.
Yichao Wang Mengyu Sun, Peng Wang
SP-HRNet: single-path neural architecture search for human pose estimation Journal Article
In: Discover Applied Sciences , 2025.
@article{Sun-das25a,
title = {SP-HRNet: single-path neural architecture search for human pose estimation},
author = {
Mengyu Sun, Yichao Wang, Peng Wang, Wuqi Gao, Qunli Li, Xiaoyan Li, Ruohai Di
},
url = {https://link.springer.com/article/10.1007/s42452-025-06846-0},
year = {2025},
date = {2025-06-01},
urldate = {2025-06-01},
journal = {Discover Applied Sciences },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4205.
Liu, Xuncheng; Zhang, Weizhan; Gong, Tieliang; Yan, Caixia; Li, Rui
Leveraging differentiable NAS and abstract genetic algorithms for optimizing on-mobile VSR performance Journal Article
In: Machine Learning , 2025.
@article{liu-ml25a,
title = {Leveraging differentiable NAS and abstract genetic algorithms for optimizing on-mobile VSR performance},
author = {
Xuncheng Liu and Weizhan Zhang and Tieliang Gong and Caixia Yan and Rui Li
},
url = {https://link.springer.com/article/10.1007/s10994-025-06801-5},
year = {2025},
date = {2025-06-01},
urldate = {2025-06-01},
journal = {Machine Learning },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4204.
Zou, Zhenwan; Wang, Bin; Chen, Tao; Chen, Jia
2025.
@bachelorthesis{zou-da25a,
title = {Research on power data security full-link monitoring technology based on alternative evolutionary graph neural architecture search and multimodal data fusion},
author = {Zhenwan Zou and Bin Wang and Tao Chen and Jia Chen
},
url = {https://link.springer.com/article/10.1007/s42452-025-07247-z},
year = {2025},
date = {2025-06-01},
urldate = {2025-06-01},
journal = {Discover Applied Sciences },
keywords = {},
pubstate = {published},
tppubtype = {bachelorthesis}
}
4203.
Song, Changwei; Ma, Yongjie; Ping, Haoyu; Sun, Lisheng
Evolutionary neural architecture search for traffic sign recognition Journal Article
In: Optoelectronics Letters, 2025.
@article{Song-ol25a,
title = {Evolutionary neural architecture search for traffic sign recognition},
author = {
Changwei Song and Yongjie Ma and Haoyu Ping and Lisheng Sun
},
url = {https://link.springer.com/article/10.1007/s11801-025-4067-z},
year = {2025},
date = {2025-06-01},
urldate = {2025-06-01},
journal = {Optoelectronics Letters},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4202.
(Ed.)
TrajGNAS: Heterogeneous Multiagent Trajectory Prediction Based on a Graph Neural Architecture Search Collection
2025.
@collection{xu-cvprw25a,
title = {TrajGNAS: Heterogeneous Multiagent Trajectory Prediction Based on a Graph Neural Architecture Search},
author = {Yunheng Xu and Jie Chen and Shuoheng Wang and Xinwen Wang},
url = {https://openaccess.thecvf.com/content/CVPR2025W/WAD/papers/Xu_TrajGNAS_Heterogeneous_Multiagent_Trajectory_Prediction_Based_on_a_Graph_Neural_CVPRW_2025_paper.pdf},
year = {2025},
date = {2025-06-01},
urldate = {2025-06-01},
booktitle = {CVPR Workshop},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
4201.
Xu, Hongyan
Deep learning-based skin cancer diagnosis PhD Thesis
2025.
@phdthesis{nokey,
title = { Deep learning-based skin cancer diagnosis},
author = {Hongyan Xu},
url = {https://unsworks.unsw.edu.au/entities/publication/753dcad7-9277-4d78-8ecb-bc0fae644fdb},
year = {2025},
date = {2025-06-01},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
4200.
Mishra, Someshwar; Singh, Baibhav; Ansari, Maruf
Tomato Leaf Disease Detection Journal Article
In: International Journal on Science and Technology (IJSAT), vol. 16, iss. 2, 2025.
@article{nokey,
title = {Tomato Leaf Disease Detection},
author = {Someshwar Mishra and Baibhav Singh and Maruf Ansari},
url = {https://www.ijsat.org/papers/2025/2/5623.pdf},
year = {2025},
date = {2025-06-01},
urldate = {2025-06-01},
journal = {International Journal on Science and Technology (IJSAT)},
volume = {16},
issue = {2},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4199.
(Ed.)
Multicriteria structural-parametric synthesis of optimal hybrid CNN structure for image processing⋆ Collection
2025.
@collection{nokey,
title = {Multicriteria structural-parametric synthesis of optimal hybrid CNN structure for image processing⋆},
author = {Illia Boryndo and Victor Sineglazov},
url = {https://ceur-ws.org/Vol-3970/PAPER13.pdf},
year = {2025},
date = {2025-06-01},
urldate = {2025-06-01},
booktitle = {SMARTINDUSTRY-2025: 2nd International Conference on Smart Automation & Robotics for Future Industry,},
journal = {SMARTINDUSTRY-2025: 2nd International Conference on Smart Automation & Robotics for Future Industry,},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
4198.
Zuo, Yingli; Wang, Lianyu; Liu, Jianxin; Feng, Shichang; Wang, Yuling; Zhu, Qi; Shao, Wei; Zhang, Daoqiang
TAFL: Task-Agnostic Feature Learner for Efficient Adaptation to Unseen Clinical Tasks based on Whole-Slide Histopathological Images Journal Article
In: IEEE Trans Med Imaging , 2025.
@article{nokey,
title = { TAFL: Task-Agnostic Feature Learner for Efficient Adaptation to Unseen Clinical Tasks based on Whole-Slide Histopathological Images },
author = {Yingli Zuo and Lianyu Wang and Jianxin Liu and Shichang Feng and Yuling Wang and Qi Zhu and Wei Shao and Daoqiang Zhang
},
url = {https://pubmed.ncbi.nlm.nih.gov/40456098/},
year = {2025},
date = {2025-06-01},
journal = { IEEE Trans Med Imaging },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4197.
K, Venkata Ratna Prabha; Bindu, Chinni Hima; Devi, K Rama
An interpretable deep learning approach for autism spectrum disorder detection in children using NASNet-mobile Journal Article
In: Biomedical Physics & Engineering Express, vol. 11, no. 4, pp. 045006, 2025.
@article{K_2025,
title = {An interpretable deep learning approach for autism spectrum disorder detection in children using NASNet-mobile},
author = {Venkata Ratna Prabha K and Chinni Hima Bindu and K Rama Devi},
url = {https://dx.doi.org/10.1088/2057-1976/addbe7},
doi = {10.1088/2057-1976/addbe7},
year = {2025},
date = {2025-06-01},
urldate = {2025-06-01},
journal = {Biomedical Physics & Engineering Express},
volume = {11},
number = {4},
pages = {045006},
publisher = {IOP Publishing},
abstract = {Autism spectrum disorder (ASD) is a multifaceted neurodevelopmental disorder featuring impaired social interactions and communication abilities engaging the individuals in a restrictive or repetitive behaviour. Though incurable early detection and intervention can reduce the severity of symptoms. Structural magnetic resonance imaging (sMRI) can improve diagnostic accuracy, facilitating early diagnosis to offer more tailored care. With the emergence of deep learning (DL), neuroimaging-based approaches for ASD diagnosis have been focused. However, many existing models lack interpretability of their decisions for diagnosis. The prime objective of this work is to perform ASD classification precisely and to interpret the classification process in a better way so as to discern the major features that are appropriate for the prediction of disorder. The proposed model employs neural architecture search network - mobile(NASNet-Mobile) model for ASD detection, which is integrated with an explainable artificial intelligence (XAI) technique called local interpretable model-agnostic explanations (LIME) for increased transparency of ASD classification. The model is trained on sMRI images of two age groups taken from autism brain imaging data exchange-I (ABIDE-I) dataset. The proposed model yielded accuracy of 0.9607, F1-score of 0.9614, specificity of 0.9774, sensitivity of 0.9451, negative predicted value (NPV) of 0.9429, positive predicted value (PPV) of 0.9783 and the diagnostic odds ratio of 745.59 for 2 to 11 years age group compared to 12 to 18 years group. These results are superior compared to other state of the art models Inception v3 and SqueezeNet.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Autism spectrum disorder (ASD) is a multifaceted neurodevelopmental disorder featuring impaired social interactions and communication abilities engaging the individuals in a restrictive or repetitive behaviour. Though incurable early detection and intervention can reduce the severity of symptoms. Structural magnetic resonance imaging (sMRI) can improve diagnostic accuracy, facilitating early diagnosis to offer more tailored care. With the emergence of deep learning (DL), neuroimaging-based approaches for ASD diagnosis have been focused. However, many existing models lack interpretability of their decisions for diagnosis. The prime objective of this work is to perform ASD classification precisely and to interpret the classification process in a better way so as to discern the major features that are appropriate for the prediction of disorder. The proposed model employs neural architecture search network - mobile(NASNet-Mobile) model for ASD detection, which is integrated with an explainable artificial intelligence (XAI) technique called local interpretable model-agnostic explanations (LIME) for increased transparency of ASD classification. The model is trained on sMRI images of two age groups taken from autism brain imaging data exchange-I (ABIDE-I) dataset. The proposed model yielded accuracy of 0.9607, F1-score of 0.9614, specificity of 0.9774, sensitivity of 0.9451, negative predicted value (NPV) of 0.9429, positive predicted value (PPV) of 0.9783 and the diagnostic odds ratio of 745.59 for 2 to 11 years age group compared to 12 to 18 years group. These results are superior compared to other state of the art models Inception v3 and SqueezeNet.
4196.
Lan, Guojun; Shi, Mingshan; Tang, Jian; He, Yiqiong; Ji, Yunbo
An efficient safety prediction and control strategy using fuzzy neural network architecture search in islanded microgrids Journal Article
In: Discover Computing , 2025.
@article{lan-dc2025a,
title = {An efficient safety prediction and control strategy using fuzzy neural network architecture search in islanded microgrids},
author = {Guojun Lan and Mingshan Shi and Jian Tang and Yiqiong He and Yunbo Ji
},
url = {https://link.springer.com/article/10.1007/s10791-025-09562-w},
year = {2025},
date = {2025-05-26},
urldate = {2025-05-26},
journal = {Discover Computing },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4195.
Shahzad, Tariq; Saqib, Sheikh Muhammad; Mazhar, Tehseen; Iqbal, Muhammad; Almogren, Ahmad; Ghadi, Yazeed Yasin; Saeed, Mamoon M.; Hamam, Habib
MobNas ensembled model for breast cancer prediction Journal Article
In: scientific reports , 2025.
@article{Shahzad-sr25a,
title = {MobNas ensembled model for breast cancer prediction},
author = {
Tariq Shahzad and Sheikh Muhammad Saqib and Tehseen Mazhar and Muhammad Iqbal and Ahmad Almogren and Yazeed Yasin Ghadi and Mamoon M. Saeed and Habib Hamam
},
url = {https://www.nature.com/articles/s41598-025-01920-4},
year = {2025},
date = {2025-05-25},
urldate = {2025-05-25},
journal = {scientific reports },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4194.
Alizadeh, Mahhya; Jameii, Seyed Mahdi; Reza, Akram
In: Multimedia Tools and Applications , 2025.
@article{Alizadeh-mta25a,
title = {An improved NSGA-II algorithm based on fuzzy logic and learning automata for automatically designing the convolutional neural network for image classification},
author = {Mahhya Alizadeh and Seyed Mahdi Jameii and Akram Reza
},
url = {https://link.springer.com/article/10.1007/s11042-025-20912-0},
year = {2025},
date = {2025-05-19},
urldate = {2025-05-19},
journal = {Multimedia Tools and Applications },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4193.
Rahman, Md Hafizur; Haider, Zafaryab; Chakraborty, Prabuddha
An automated multi parameter neural architecture discovery framework using ChatGPT in the backend Journal Article
In: Scientific Reports, 2025.
@article{Rahman-sr25a,
title = {An automated multi parameter neural architecture discovery framework using ChatGPT in the backend},
author = {Md Hafizur Rahman and Zafaryab Haider and Prabuddha Chakraborty
},
url = {https://www.nature.com/articles/s41598-025-97378-5},
year = {2025},
date = {2025-05-15},
urldate = {2025-05-15},
journal = {Scientific Reports},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4192.
Gopal, Bhavna
2025.
@phdthesis{nokey,
title = {Optimizing Deep Neural Networks: Leveraging Structural Characteristics for Enhanced NAS and Adversarial Robustness},
author = {Bhavna Gopal },
url = {https://www.proquest.com/docview/3206229953?pq-origsite=gscholar&fromopenview=true&sourcetype=Dissertations%20&%20Theses},
year = {2025},
date = {2025-05-02},
urldate = {2025-05-02},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
4191.
Athmani, Khaled; Almeasar, Kamal Saleh; Atiki, Elhoussine; Habal, Adel Hassan Yahya; Taallah, Bachir; Guettala, Abdelhamid
Machine learning methods for predicting the durability behavior of earth mortars with date palm ash Journal Article
In: Asian Journal of Civil Engineering , 2025.
@article{Athmani-ajce25a,
title = {Machine learning methods for predicting the durability behavior of earth mortars with date palm ash},
author = {
Khaled Athmani and Kamal Saleh Almeasar and Elhoussine Atiki and Adel Hassan Yahya Habal and Bachir Taallah and Abdelhamid Guettala
},
url = {https://link.springer.com/article/10.1007/s42107-025-01365-0},
year = {2025},
date = {2025-05-02},
urldate = {2025-05-02},
journal = {Asian Journal of Civil Engineering },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4190.
Boukela, Lynda; Branlard, Julien; Eichler, Annika
Exploring NAS for anomaly detection in superconducting cavities of particle accelerators Journal Article
In: Front. Phys., 2025.
@article{nokey,
title = {Exploring NAS for anomaly detection in superconducting cavities of particle accelerators},
author = {Lynda Boukela and Julien Branlard and Annika Eichler},
url = {https://www.frontiersin.org/journals/physics/articles/10.3389/fphy.2025.1553993/full},
doi = {10.3389/fphy.2025.1553993},
year = {2025},
date = {2025-05-02},
journal = {Front. Phys.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4189.
(Ed.)
CG-CANTS-N: A Versatile Graph-Based Framework for Scalable and Adaptive Problem Solving Across Domains Collection Forthcoming
Forthcoming.
@collection{nokey,
title = {CG-CANTS-N: A Versatile Graph-Based Framework for Scalable and Adaptive Problem Solving Across Domains},
author = {AbdElRahman ElSaid and Travis Desel },
url = {https://people.uncw.edu/elsaida/publications_files/cg_cants_n.pdf},
year = {2025},
date = {2025-05-02},
urldate = {2025-05-02},
booktitle = {GECCO ’25 },
keywords = {},
pubstate = {forthcoming},
tppubtype = {collection}
}
4188.
Rubbani, Syeda
Neuroevolutionary Optimization of Shannon’s Capacity in Edge AI Protocols for M2M Communication Technical Report
2025.
@techreport{nokey,
title = {Neuroevolutionary Optimization of Shannon’s Capacity in Edge AI Protocols for M2M Communication},
author = {Syeda Rubbani},
url = {https://www.researchsquare.com/article/rs-6621997/v1},
year = {2025},
date = {2025-05-02},
urldate = {2025-05-02},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
4187.
Gupta, Rajat; Jindal, Rakesh
Impact of Too Many Neural Network Layers on Overfitting Journal Article
In: International Journal of Computer Science and Mobile Computing, 2025.
@article{gupta-ijcsmc25a,
title = {Impact of Too Many Neural Network Layers on Overfitting},
author = {Rajat Gupta and Rakesh Jindal},
url = {https://ijcsmc.com/docs/papers/May2025/V14I5202502.pdf},
year = {2025},
date = {2025-05-02},
urldate = {2025-05-02},
journal = {International Journal of Computer Science and Mobile Computing},
keywords = {},
pubstate = {published},
tppubtype = {article}
}