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
3635.
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.
3634.
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.
2025
3633.
Jiang, Zhiying; Liu, Risheng; Yang, Shuzhou; Zhang, Zengxi; Fan, Xin
DRNet: Learning a dynamic recursion network for chaotic rain streak removal Journal Article
In: Pattern Recognition, vol. 158, pp. 111004, 2025, ISSN: 0031-3203.
@article{JIANG2025111004,
title = {DRNet: Learning a dynamic recursion network for chaotic rain streak removal},
author = {Zhiying Jiang and Risheng Liu and Shuzhou Yang and Zengxi Zhang and Xin Fan},
url = {https://www.sciencedirect.com/science/article/pii/S0031320324007556},
doi = {https://doi.org/10.1016/j.patcog.2024.111004},
issn = {0031-3203},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
journal = {Pattern Recognition},
volume = {158},
pages = {111004},
abstract = {Image deraining refers to removing the visible rain streaks to restore the rain-free scenes. Existing methods rely on manually crafted networks to model the distribution of rain streaks. However, complex scenes disrupt the uniformity of rain streak characteristics assumed in ideal conditions, resulting in rain streaks of varying directions, intensities, and brightness intersecting within the same scene, challenging the deep learning based deraining performance. To address the chaotic rain streak removal, we handle the rain streaks with similar distribution characteristics in the same layer and employ a dynamic recursive mechanism to extract and unveil them progressively. Specifically, we employ neural architecture search to determine the models of different rain streaks. To avoid the loss of texture details associated with overly deep structures, we integrate multi-scale modeling and cross-scale recruitment within the dynamic structure. Considering the application of real-world scenes, we incorporate contrastive training to improve the generalization. Experimental results indicate superior performance in rain streak depiction compared to existing methods. Practical evaluation confirms its effectiveness in object detection and semantic segmentation tasks. Code is available at https://github.com/Jzy2017/DRNet.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Image deraining refers to removing the visible rain streaks to restore the rain-free scenes. Existing methods rely on manually crafted networks to model the distribution of rain streaks. However, complex scenes disrupt the uniformity of rain streak characteristics assumed in ideal conditions, resulting in rain streaks of varying directions, intensities, and brightness intersecting within the same scene, challenging the deep learning based deraining performance. To address the chaotic rain streak removal, we handle the rain streaks with similar distribution characteristics in the same layer and employ a dynamic recursive mechanism to extract and unveil them progressively. Specifically, we employ neural architecture search to determine the models of different rain streaks. To avoid the loss of texture details associated with overly deep structures, we integrate multi-scale modeling and cross-scale recruitment within the dynamic structure. Considering the application of real-world scenes, we incorporate contrastive training to improve the generalization. Experimental results indicate superior performance in rain streak depiction compared to existing methods. Practical evaluation confirms its effectiveness in object detection and semantic segmentation tasks. Code is available at https://github.com/Jzy2017/DRNet.
3632.
Rahman, Abdur; Street, Jason; Wooten, James; Marufuzzaman, Mohammad; Gude, Veera G.; Buchanan, Randy; Wang, Haifeng
MoistNet: Machine vision-based deep learning models for wood chip moisture content measurement Journal Article
In: Expert Systems with Applications, vol. 259, pp. 125363, 2025, ISSN: 0957-4174.
@article{Rahman_2025,
title = {MoistNet: Machine vision-based deep learning models for wood chip moisture content measurement},
author = {Abdur Rahman and Jason Street and James Wooten and Mohammad Marufuzzaman and Veera G. Gude and Randy Buchanan and Haifeng Wang},
url = {http://dx.doi.org/10.1016/j.eswa.2024.125363},
doi = {10.1016/j.eswa.2024.125363},
issn = {0957-4174},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
journal = {Expert Systems with Applications},
volume = {259},
pages = {125363},
publisher = {Elsevier BV},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
3631.
Öcal, Göktuğ; Özgövde, Atay
Network-aware federated neural architecture search Journal Article
In: Future Generation Computer Systems, vol. 162, pp. 107475, 2025, ISSN: 0167-739X.
@article{OCAL2025107475,
title = {Network-aware federated neural architecture search},
author = {Göktuğ Öcal and Atay Özgövde},
url = {https://www.sciencedirect.com/science/article/pii/S0167739X24004205},
doi = {https://doi.org/10.1016/j.future.2024.07.053},
issn = {0167-739X},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
journal = {Future Generation Computer Systems},
volume = {162},
pages = {107475},
abstract = {The cooperation between Deep Learning (DL) and edge devices has further advanced technological developments, allowing smart devices to serve as both data sources and endpoints for DL-powered applications. However, the success of DL relies on optimal Deep Neural Network (DNN) architectures, and manually developing such systems requires extensive expertise and time. Neural Architecture Search (NAS) has emerged to automate the search for the best-performing neural architectures. Meanwhile, Federated Learning (FL) addresses data privacy concerns by enabling collaborative model development without exchanging the private data of clients. In a FL system, network limitations can lead to biased model training, slower convergence, and increased communication overhead. On the other hand, traditional DNN architecture design, emphasizing validation accuracy, often overlooks computational efficiency and size constraints of edge devices. This research aims to develop a comprehensive framework that effectively balances trade-offs between model performance, communication efficiency, and the incorporation of FL into an iterative NAS algorithm. This framework aims to overcome challenges by addressing the specific requirements of FL, optimizing DNNs through NAS, and ensuring computational efficiency while considering the network constraints of edge devices. To address these challenges, we introduce Network-Aware Federated Neural Architecture Search (NAFNAS), an open-source federated neural network pruning framework with network emulation support. Through comprehensive testing, we demonstrate the feasibility of our approach, efficiently reducing DNN size and mitigating communication challenges. Additionally, we propose Network and Distribution Aware Client Grouping (NetDAG), a novel client grouping algorithm tailored for FL with diverse DNN architectures, considerably enhancing efficiency of communication rounds and update balance.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The cooperation between Deep Learning (DL) and edge devices has further advanced technological developments, allowing smart devices to serve as both data sources and endpoints for DL-powered applications. However, the success of DL relies on optimal Deep Neural Network (DNN) architectures, and manually developing such systems requires extensive expertise and time. Neural Architecture Search (NAS) has emerged to automate the search for the best-performing neural architectures. Meanwhile, Federated Learning (FL) addresses data privacy concerns by enabling collaborative model development without exchanging the private data of clients. In a FL system, network limitations can lead to biased model training, slower convergence, and increased communication overhead. On the other hand, traditional DNN architecture design, emphasizing validation accuracy, often overlooks computational efficiency and size constraints of edge devices. This research aims to develop a comprehensive framework that effectively balances trade-offs between model performance, communication efficiency, and the incorporation of FL into an iterative NAS algorithm. This framework aims to overcome challenges by addressing the specific requirements of FL, optimizing DNNs through NAS, and ensuring computational efficiency while considering the network constraints of edge devices. To address these challenges, we introduce Network-Aware Federated Neural Architecture Search (NAFNAS), an open-source federated neural network pruning framework with network emulation support. Through comprehensive testing, we demonstrate the feasibility of our approach, efficiently reducing DNN size and mitigating communication challenges. Additionally, we propose Network and Distribution Aware Client Grouping (NetDAG), a novel client grouping algorithm tailored for FL with diverse DNN architectures, considerably enhancing efficiency of communication rounds and update balance.
2024
3630.
Zhou, Ao; Yang, Jianlei; Qi, Yingjie; Qiao, Tong; Shi, Yumeng; Duan, Cenlin; Zhao, Weisheng; Hu, Chunming
HGNAS: Hardware-Aware Graph Neural Architecture Search for Edge Devices Journal Article
In: IEEE Transactions on Computers, vol. 73, no. 12, pp. 2693-2707, 2024, ISSN: 1557-9956.
@article{10644077,
title = { HGNAS: Hardware-Aware Graph Neural Architecture Search for Edge Devices },
author = {Ao Zhou and Jianlei Yang and Yingjie Qi and Tong Qiao and Yumeng Shi and Cenlin Duan and Weisheng Zhao and Chunming Hu},
url = {https://doi.ieeecomputersociety.org/10.1109/TC.2024.3449108},
doi = {10.1109/TC.2024.3449108},
issn = {1557-9956},
year = {2024},
date = {2024-12-01},
urldate = {2024-12-01},
journal = {IEEE Transactions on Computers},
volume = {73},
number = {12},
pages = {2693-2707},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {Graph Neural Networks (GNNs) are becoming increasingly popular for graph-based learning tasks such as point cloud processing due to their state-of-the-art (SOTA) performance. Nevertheless, the research community has primarily focused on improving model expressiveness, lacking consideration of how to design efficient GNN models for edge scenarios with real-time requirements and limited resources. Examining existing GNN models reveals varied execution across platforms and frequent Out-Of-Memory (OOM) problems, highlighting the need for hardware-aware GNN design. To address this challenge, this work proposes a novel hardware-aware graph neural architecture search framework tailored for resource constraint edge devices, namely HGNAS. To achieve hardware awareness, HGNAS integrates an efficient GNN hardware performance predictor that evaluates the latency and peak memory usage of GNNs in milliseconds. Meanwhile, we study GNN memory usage during inference and offer a peak memory estimation method, enhancing the robustness of architecture evaluations when combined with predictor outcomes. Furthermore, HGNAS constructs a fine-grained design space to enable the exploration of extreme performance architectures by decoupling the GNN paradigm. In addition, the multi-stage hierarchical search strategy is leveraged to facilitate the navigation of huge candidates, which can reduce the single search time to a few GPU hours. To the best of our knowledge, HGNAS is the first automated GNN design framework for edge devices, and also the first work to achieve hardware awareness of GNNs across different platforms. Extensive experiments across various applications and edge devices have proven the superiority of HGNAS. It can achieve up to a $10.6boldsymboltimes$10.6× speedup and an $82.5%$82.5% peak memory reduction with negligible accuracy loss compared to DGCNN on ModelNet40.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Graph Neural Networks (GNNs) are becoming increasingly popular for graph-based learning tasks such as point cloud processing due to their state-of-the-art (SOTA) performance. Nevertheless, the research community has primarily focused on improving model expressiveness, lacking consideration of how to design efficient GNN models for edge scenarios with real-time requirements and limited resources. Examining existing GNN models reveals varied execution across platforms and frequent Out-Of-Memory (OOM) problems, highlighting the need for hardware-aware GNN design. To address this challenge, this work proposes a novel hardware-aware graph neural architecture search framework tailored for resource constraint edge devices, namely HGNAS. To achieve hardware awareness, HGNAS integrates an efficient GNN hardware performance predictor that evaluates the latency and peak memory usage of GNNs in milliseconds. Meanwhile, we study GNN memory usage during inference and offer a peak memory estimation method, enhancing the robustness of architecture evaluations when combined with predictor outcomes. Furthermore, HGNAS constructs a fine-grained design space to enable the exploration of extreme performance architectures by decoupling the GNN paradigm. In addition, the multi-stage hierarchical search strategy is leveraged to facilitate the navigation of huge candidates, which can reduce the single search time to a few GPU hours. To the best of our knowledge, HGNAS is the first automated GNN design framework for edge devices, and also the first work to achieve hardware awareness of GNNs across different platforms. Extensive experiments across various applications and edge devices have proven the superiority of HGNAS. It can achieve up to a $10.6boldsymboltimes$10.6× speedup and an $82.5%$82.5% peak memory reduction with negligible accuracy loss compared to DGCNN on ModelNet40.
3629.
Li, Gai; Cao, Chunhong; Fu, Huawei; Li, Xingxing; Gao, Xieping
Modeling Functional Brain Networks for ADHD via Spatial Preservation-Based Neural Architecture Search Journal Article
In: IEEE J Biomed Health Inform , 2024.
@article{Li-BHI24a,
title = { Modeling Functional Brain Networks for ADHD via Spatial Preservation-Based Neural Architecture Search },
author = {Gai Li and Chunhong Cao and Huawei Fu and Xingxing Li and Xieping Gao
},
url = {https://pubmed.ncbi.nlm.nih.gov/39167518/},
year = {2024},
date = {2024-11-28},
urldate = {2024-11-28},
journal = { IEEE J Biomed Health Inform },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
3628.
Jia Ma,; Ma, Xinru; Li, Chulian; Li, Tongyan
Vehicle-drone collaborative distribution path planning based on neural architecture search under the influence of carbon emissions Journal Article
In: Discover Computing , vol. 27, 2024.
@article{ma-dc24a,
title = {Vehicle-drone collaborative distribution path planning based on neural architecture search under the influence of carbon emissions},
author = {
Jia Ma, and Xinru Ma and Chulian Li and Tongyan Li
},
url = {https://link.springer.com/article/10.1007/s10791-024-09469-y},
year = {2024},
date = {2024-11-11},
urldate = {2024-11-11},
journal = {Discover Computing },
volume = {27},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
3627.
Ma, QuanGong; Hao, ChaoLong; Yang, XuKui; Qian, LongLong; Zhang, Hao; Si, NianWen; Xu, MinChen; Qu, Dan
Continuous evolution for efficient quantum architecture search Journal Article
In: EPJ Quantum Technology , 2024.
@article{maeükqt24a,
title = {Continuous evolution for efficient quantum architecture search},
author = {
QuanGong Ma and ChaoLong Hao and XuKui Yang and LongLong Qian and Hao Zhang and NianWen Si and MinChen Xu and Dan Qu
},
url = {https://link.springer.com/article/10.1140/epjqt/s40507-024-00265-7},
year = {2024},
date = {2024-09-06},
urldate = {2024-09-06},
journal = {EPJ Quantum Technology },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
3626.
Zhao, ZiHao; Tang, XiangHong; Lu, JianGuang; Huang, Yong
Lightweight graph neural network architecture search based on heuristic algorithms Journal Article
In: International Journal of Machine Learning and Cybernetics , 2024.
@article{zhao-ijmlc24a,
title = {Lightweight graph neural network architecture search based on heuristic algorithms},
author = {ZiHao Zhao and XiangHong Tang and JianGuang Lu and Yong Huang
},
url = {https://link.springer.com/article/10.1007/s13042-024-02356-4},
year = {2024},
date = {2024-09-04},
urldate = {2024-09-04},
journal = { International Journal of Machine Learning and Cybernetics },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
3625.
(Ed.)
2024.
@collection{Ringhofer-daf24a,
title = {BALANCING ERROR AND LATENCY OF BLACK-BOX MODELS FOR AUDIO EFFECTS USING HARDWARE-AWARE NEURAL ARCHITECTURE SEARCH},
author = {Christopher Ringhofer and Alexa Gnoss and Gregor Schiele},
url = {https://www.dafx.de/paper-archive/2024/papers/DAFx24_paper_44.pdf},
year = {2024},
date = {2024-09-03},
urldate = {2024-09-03},
booktitle = {Proceedings of the 27th International Conference on Digital Audio Effects (DAFx24) },
journal = {Proceedings of the 27th International Conference on Digital Audio Effects (DAFx24) },
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
3624.
(Ed.)
2024.
@collection{park-interspeech24a,
title = {RepTor: Re-parameterizable Temporal Convolution for Keyword Spotting via Differentiable Kernel Search},
author = {Eunik Park and Daehyun Ahn and Hyungjun Kim},
url = {https://www.isca-archive.org/interspeech_2024/park24_interspeech.pdf},
year = {2024},
date = {2024-09-01},
urldate = {2024-09-01},
booktitle = {Interspeech 2024},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
3623.
Dai, Menghang; Liu, Zhiliang; He, Zixiao
Wafer defect pattern recognition based on differentiable architecture search with dual attention module Journal Article
In: Measurement Science and Technology, vol. 35, no. 12, pp. 125102, 2024.
@article{Dai_2024,
title = {Wafer defect pattern recognition based on differentiable architecture search with dual attention module},
author = {Menghang Dai and Zhiliang Liu and Zixiao He},
url = {https://dx.doi.org/10.1088/1361-6501/ad730b},
doi = {10.1088/1361-6501/ad730b},
year = {2024},
date = {2024-09-01},
urldate = {2024-09-01},
journal = {Measurement Science and Technology},
volume = {35},
number = {12},
pages = {125102},
publisher = {IOP Publishing},
abstract = {Wafer defect pattern recognition is a crucial process for ensuring chip production quality. Due to the complexity of wafer production processes, wafers often contain multiple defect patterns simultaneously, making it challenging for existing deep learning algorithms designed for single defect patterns to achieve optimal performance. To address this issue, this paper proposes a dual attention integrated differentiable architecture search (DA-DARTS), which can automatically search for suitable neural network architectures, significantly simplifying the architecture design process. Furthermore, the integration of DA greatly enhances the efficiency of the architecture search. We validated our proposed method on the MixedWM38 dataset, and experimental results indicate that the DA-DARTS method achieves higher pattern recognition accuracy under mixed defect patterns compared to baseline methods, maintaining performance stability even on imbalanced datasets.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Wafer defect pattern recognition is a crucial process for ensuring chip production quality. Due to the complexity of wafer production processes, wafers often contain multiple defect patterns simultaneously, making it challenging for existing deep learning algorithms designed for single defect patterns to achieve optimal performance. To address this issue, this paper proposes a dual attention integrated differentiable architecture search (DA-DARTS), which can automatically search for suitable neural network architectures, significantly simplifying the architecture design process. Furthermore, the integration of DA greatly enhances the efficiency of the architecture search. We validated our proposed method on the MixedWM38 dataset, and experimental results indicate that the DA-DARTS method achieves higher pattern recognition accuracy under mixed defect patterns compared to baseline methods, maintaining performance stability even on imbalanced datasets.
3622.
Ouertatani, Houssem; Maxim, Cristian; Niar, Smail; Talbi, El-Ghazali
Accelerated NAS via pretrained ensembles and multi-fidelity Bayesian Optimization Proceedings Article
In: 33rd International Conference on Artificial Neural Networks (ICANN), Lugano, Switzerland, 2024.
@inproceedings{ouertatani:hal-04611343,
title = {Accelerated NAS via pretrained ensembles and multi-fidelity Bayesian Optimization},
author = {Houssem Ouertatani and Cristian Maxim and Smail Niar and El-Ghazali Talbi},
url = {https://hal.science/hal-04611343},
year = {2024},
date = {2024-09-01},
urldate = {2024-09-01},
booktitle = {33rd International Conference on Artificial Neural Networks (ICANN)},
address = {Lugano, Switzerland},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
3621.
Xiao, Jiamin; Yu, Kuoyong; Zhao, Bo; Liu, Derong
Evolutionary Neural Architecture Search with Performance Predictor Based on Hybrid Encodings Technical Report
2024.
@techreport{nokey,
title = {Evolutionary Neural Architecture Search with Performance Predictor Based on Hybrid Encodings},
author = {Jiamin Xiao and Kuoyong Yu and Bo Zhao and Derong Liu},
url = {https://openreview.net/pdf?id=TK6DaN7I5r},
year = {2024},
date = {2024-08-30},
urldate = {2024-08-30},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
3620.
Ajani, Oladayo S.; Darlan, Daison; Ivan, Dzeuban Fenyom; Mallipeddi, Rammohan
Multi-indicator based multi-objective evolutionary algorithm with application to neural architecture search Journal Article
In: International Journal of Machine Learning and Cybernetics , 2024.
@article{Ajani-ijmlc24a,
title = {Multi-indicator based multi-objective evolutionary algorithm with application to neural architecture search},
author = {Oladayo S. Ajani and Daison Darlan and Dzeuban Fenyom Ivan and Rammohan Mallipeddi
},
url = {https://link.springer.com/article/10.1007/s13042-024-02300-6},
year = {2024},
date = {2024-08-27},
urldate = {2024-08-27},
journal = {International Journal of Machine Learning and Cybernetics },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
3619.
Moutaouekkil, Mohammed A.; Karkri, Aboulkacem; Koulali, Mohammed A.; Taybi, Chakib; Kahlaoui, Mohammed
Plant Root Characterization Using Ground-Penetrating Radar with Deep Learning Journal Article
In: Arabian Journal for Science and Engineering, 2024.
@article{Moutaouekkil-ajse24a,
title = {Plant Root Characterization Using Ground-Penetrating Radar with Deep Learning},
author = {Mohammed A. Moutaouekkil and Aboulkacem Karkri and Mohammed A. Koulali and Chakib Taybi and Mohammed Kahlaoui
},
url = {https://link.springer.com/article/10.1007/s13369-024-09502-8},
year = {2024},
date = {2024-08-22},
urldate = {2024-08-22},
journal = { Arabian Journal for Science and Engineering},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
3618.
Mebirouk, Nadjib; Amrane, Moussa; Messast, Salah; Mazouzi, Smaine
In: Modeling Earth Systems and Environment , vol. 10, 2024.
@article{Mebirouk-mese24a,
title = {Enhanced analysis of landslide susceptibility mapping in the proximity of main roads in the province of Skikda, Algeria: using NAS for efficient performance and faster processing},
author = {Nadjib Mebirouk and Moussa Amrane and Salah Messast and Smaine Mazouzi
},
url = {https://link.springer.com/article/10.1007/s40808-024-02129-6},
year = {2024},
date = {2024-08-20},
urldate = {2024-08-20},
journal = {Modeling Earth Systems and Environment },
volume = {10},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
3617.
(Ed.)
Medical Neural Architecture Search: Survey and Taxonomy Collection
2024.
@collection{Benmeziane-ijcai24a,
title = {Medical Neural Architecture Search: Survey and Taxonomy},
author = {Hadjer Benmeziane and Imane Hamzaoui and Kaoutar El Maghraoui and Kaoutar El Maghraoui},
url = {https://www.ijcai.org/proceedings/2024/0878.pdf},
year = {2024},
date = {2024-08-03},
urldate = {2024-08-03},
booktitle = {IJCAI 2024},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
3616.
Zhang, Jinnian; Chen, Weijie; Joshi, Tanmayee; Uyanik, Meltem; Zhang, Xiaomin; Loh, Po-Ling; Jog, Varun; Bruce, Richard; Garrett, John; McMillan, Alan
RobMedNAS: searching robust neural network architectures for medical image synthesis Journal Article
In: Biomedical Physics & Engineering Express, vol. 10, no. 5, pp. 055029, 2024.
@article{Zhang_2024,
title = {RobMedNAS: searching robust neural network architectures for medical image synthesis},
author = {Jinnian Zhang and Weijie Chen and Tanmayee Joshi and Meltem Uyanik and Xiaomin Zhang and Po-Ling Loh and Varun Jog and Richard Bruce and John Garrett and Alan McMillan},
url = {https://dx.doi.org/10.1088/2057-1976/ad6e87},
doi = {10.1088/2057-1976/ad6e87},
year = {2024},
date = {2024-08-01},
urldate = {2024-08-01},
journal = {Biomedical Physics & Engineering Express},
volume = {10},
number = {5},
pages = {055029},
publisher = {IOP Publishing},
abstract = {Investigating U-Net model robustness in medical image synthesis against adversarial perturbations, this study introduces RobMedNAS, a neural architecture search strategy for identifying resilient U-Net configurations. Through retrospective analysis of synthesized CT from MRI data, employing Dice coefficient and mean absolute error metrics across critical anatomical areas, the study evaluates traditional U-Net models and RobMedNAS-optimized models under adversarial attacks. Findings demonstrate RobMedNAS’s efficacy in enhancing U-Net resilience without compromising on accuracy, proposing a novel pathway for robust medical image processing.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Investigating U-Net model robustness in medical image synthesis against adversarial perturbations, this study introduces RobMedNAS, a neural architecture search strategy for identifying resilient U-Net configurations. Through retrospective analysis of synthesized CT from MRI data, employing Dice coefficient and mean absolute error metrics across critical anatomical areas, the study evaluates traditional U-Net models and RobMedNAS-optimized models under adversarial attacks. Findings demonstrate RobMedNAS’s efficacy in enhancing U-Net resilience without compromising on accuracy, proposing a novel pathway for robust medical image processing.
3615.
Jeevidha, S. Saraswathi S.
Learning Methods and Parameters used in Neural Architecture Search for Image Classification Journal Article
In: International Journal of Computer Applications, vol. 186, no. 32, pp. 19-24, 2024, ISSN: 0975-8887.
@article{10.5120/ijca2024923857,
title = {Learning Methods and Parameters used in Neural Architecture Search for Image Classification},
author = {S. Saraswathi S. Jeevidha},
url = {https://ijcaonline.org/archives/volume186/number32/learning-methods-and-parameters-used-in-neural-architecture-search-for-image-classification/},
doi = {10.5120/ijca2024923857},
issn = {0975-8887},
year = {2024},
date = {2024-08-01},
urldate = {2024-08-01},
journal = {International Journal of Computer Applications},
volume = {186},
number = {32},
pages = {19-24},
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
3614.
Improved Learning Through Neural Component Search PhD Thesis
2024.
@phdthesis{morgan-phds24a,
title = {Improved Learning Through Neural Component Search},
url = {https://shareok.org/handle/11244/340526},
year = {2024},
date = {2024-08-01},
urldate = {2024-08-01},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
3613.
(Ed.)
A COMPARATIVE STUDY: DEEPFAKE VIDEO DETECTION WITH NASNETS AND LSTM Collection
2024.
@collection{nokey,
title = {A COMPARATIVE STUDY: DEEPFAKE VIDEO DETECTION WITH NASNETS AND LSTM},
author = {Farmanuddin FARMAN and Yılmaz ATAY and Cagri SAHIN},
url = {https://www.researchgate.net/profile/Farmanuddin-Farman/publication/381902059_A_COMPARATIVE_STUDY_DEEPFAKE_VIDEO_DETECTION_WITH_NASNETS_AND_LSTM/links/668408822aa57f3b82688f25/A-COMPARATIVE-STUDY-DEEPFAKE-VIDEO-DETECTION-WITH-NASNETS-AND-LSTM.pdf},
year = {2024},
date = {2024-08-01},
urldate = {2024-08-01},
booktitle = {12TH INTERNATIONAL İSTANBUL SCIENTIFIC RESEARCH CONGRESS PROCEEDINGS BOOK},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
3612.
Ge, Wanying
Spoofing-robust Automatic Speaker Verification: Architecture, Explainability and Joint Optimisation PhD Thesis
2024.
@phdthesis{Ge-phd24a,
title = {Spoofing-robust Automatic Speaker Verification: Architecture, Explainability and Joint Optimisation},
author = {Wanying Ge},
url = {https://theses.hal.science/tel-04633370/document},
year = {2024},
date = {2024-08-01},
urldate = {2024-08-01},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
3611.
Hosseini, Ramtin
Trustworthy Neural Architecture Search PhD Thesis
2024.
@phdthesis{Hosseini-phd24a,
title = {Trustworthy Neural Architecture Search},
author = {Hosseini, Ramtin},
url = {https://escholarship.org/content/qt7tr2f8zx/qt7tr2f8zx.pdf},
year = {2024},
date = {2024-08-01},
urldate = {2024-08-01},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
3610.
Baniata, Hamza
SoK: quantum computing methods for machine learning optimization Journal Article
In: Quantum Machine Intelligence , vol. 6, 2024.
@article{Baniata-quantumMl24a,
title = {SoK: quantum computing methods for machine learning optimization},
author = {Hamza Baniata },
url = {https://link.springer.com/article/10.1007/s42484-024-00180-1},
year = {2024},
date = {2024-07-24},
urldate = {2024-07-24},
journal = {Quantum Machine Intelligence },
volume = {6},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
3609.
Wu, Ruoyou; Li, Cheng; Zou, Juan; Liu, Xinfeng; Zheng, Hairong; Wang, Shanshan
Generalizable Reconstruction for Accelerating MR Imaging via Federated Learning with Neural Architecture Search Journal Article
In: IEEE Trans Med Imaging . , 2024.
@article{Wu-TMI24a,
title = { Generalizable Reconstruction for Accelerating MR Imaging via Federated Learning with Neural Architecture Search },
author = {Ruoyou Wu and Cheng Li and Juan Zou and Xinfeng Liu and Hairong Zheng and Shanshan Wang
},
url = {https://pubmed.ncbi.nlm.nih.gov/39037877/},
doi = {10.1109/TMI.2024.3432388 },
year = {2024},
date = {2024-07-22},
urldate = {2024-07-22},
journal = { IEEE Trans Med Imaging . },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
3608.
Huang, Chien Yu; Tsai, Cheng-Che; Hwang, Lisa Alice; Kang, Bor-Hwang; Lin, Yaoh-Shiang; Su, Hsing-Hao; Shen, Guan‐Ting; Hsieh, Jun-Wei
SCC-NET: Segmentation of Clinical Cancer image for Head and Neck Squamous Cell Carcinoma Technical Report
2024.
@techreport{yu-24a,
title = {SCC-NET: Segmentation of Clinical Cancer image for Head and Neck Squamous Cell Carcinoma},
author = {Chien Yu Huang and Cheng-Che Tsai and Lisa Alice Hwang and Bor-Hwang Kang and Yaoh-Shiang Lin and Hsing-Hao Su and Guan‐Ting Shen and Jun-Wei Hsieh
},
url = {https://www.researchsquare.com/article/rs-4577408/v1},
year = {2024},
date = {2024-07-16},
urldate = {2024-07-16},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
3607.
Asiimwe, Arnold; Das, William; Benmeziane, Hadjer; Maghraoui, Kaoutar El
EDGE2024, 2024.
@conference{Asiimwe-edge24a,
title = {EfficientMedSAM: Accelerating Medical Image Segmentation via Neural Architecture Search and Knowledge Distillation},
author = {Arnold Asiimwe and William Das and Hadjer Benmeziane and Kaoutar El Maghraoui},
url = {https://research.ibm.com/publications/efficientmedsam-accelerating-medical-image-segmentation-via-neural-architecture-search-and-knowledge-distillation},
year = {2024},
date = {2024-07-07},
urldate = {2024-07-07},
booktitle = {EDGE2024},
journal = {EDGE 2024},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
3606.
Braatz, Yannick; Soliman, Taha; Rai, Shubham; Rieber, Dennis Sebastian; Bringmann, Oliver
CoNAX: Towards Comprehensive Co-Design Neural Architecture Search Using HW Abstractions Proceedings Article
In: 2024 IEEE 35th International Conference on Application-specific Systems, Architectures and Processors (ASAP), pp. 8-16, IEEE Computer Society, Los Alamitos, CA, USA, 2024.
@inproceedings{10631099,
title = { CoNAX: Towards Comprehensive Co-Design Neural Architecture Search Using HW Abstractions },
author = {Yannick Braatz and Taha Soliman and Shubham Rai and Dennis Sebastian Rieber and Oliver Bringmann},
url = {https://doi.ieeecomputersociety.org/10.1109/ASAP61560.2024.00013},
doi = {10.1109/ASAP61560.2024.00013},
year = {2024},
date = {2024-07-01},
urldate = {2024-07-01},
booktitle = {2024 IEEE 35th International Conference on Application-specific Systems, Architectures and Processors (ASAP)},
pages = {8-16},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {HW-aware neural architecture search (HW-NAS) aims to yield high-accuracy neural network (NN) architectures by automatically exploring multiple architectural parameters of potential network candidates. In most HW-NAS approaches, the HW parameter search space is limited. Hence, HW awareness is tied to only a few degrees of design freedom, leading to the following sub-optimalities - First, it restricts exploration of HW parameters, which can potentially lead to better network candidates; Second, HW-NAS is still entirely a software-centric process where HW-awareness is taken care by an HW function exposed to the NAS process and is oblivious to the actual deployment. To tackle the above challenges, this paper proposes a Co-Design Neural Architecture Search (Co-NAS) approach that simultaneously explores hardware and neural architecture variations, thus allowing for full system optimization. By connecting the mutual impact of variable neural networks and HW parameters on the network's prediction accuracy and on-device efficiency in a shared optimization loop, Co-Nas finds designs of optimum performance and enables HW/SW Co-Design. This work aims to enable more diverse HW search spaces (higher degrees of design freedom) for ML accelerators (such as using a virtual prototype) and efficient exploration by integrating abstract ML accelerator and NN architecture modeling into a comprehensive Co-Nas environment. In our experiments, we explore hardware variations of a baseline accelerator architecture to demonstrate how our work can help find designs with better hardware latency and comparable network accuracy. Designs yielded by our framework provide a speedup of $1.4times$ compared to the baseline on a restricted SW search space at the same HW resources.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
HW-aware neural architecture search (HW-NAS) aims to yield high-accuracy neural network (NN) architectures by automatically exploring multiple architectural parameters of potential network candidates. In most HW-NAS approaches, the HW parameter search space is limited. Hence, HW awareness is tied to only a few degrees of design freedom, leading to the following sub-optimalities - First, it restricts exploration of HW parameters, which can potentially lead to better network candidates; Second, HW-NAS is still entirely a software-centric process where HW-awareness is taken care by an HW function exposed to the NAS process and is oblivious to the actual deployment. To tackle the above challenges, this paper proposes a Co-Design Neural Architecture Search (Co-NAS) approach that simultaneously explores hardware and neural architecture variations, thus allowing for full system optimization. By connecting the mutual impact of variable neural networks and HW parameters on the network's prediction accuracy and on-device efficiency in a shared optimization loop, Co-Nas finds designs of optimum performance and enables HW/SW Co-Design. This work aims to enable more diverse HW search spaces (higher degrees of design freedom) for ML accelerators (such as using a virtual prototype) and efficient exploration by integrating abstract ML accelerator and NN architecture modeling into a comprehensive Co-Nas environment. In our experiments, we explore hardware variations of a baseline accelerator architecture to demonstrate how our work can help find designs with better hardware latency and comparable network accuracy. Designs yielded by our framework provide a speedup of $1.4times$ compared to the baseline on a restricted SW search space at the same HW resources.
3605.
(Ed.)
Are Large Language Models Good Neural Architecture Generators for Edge? Collection
2024.
@collection{Benmeziane-edge24a,
title = {Are Large Language Models Good Neural Architecture Generators for Edge?},
author = {Hadjer Benmeziane and Kaoutar El Maghraoui},
url = {https://research.ibm.com/publications/are-large-language-models-good-neural-architecture-generators-for-edge},
year = {2024},
date = {2024-07-01},
urldate = {2024-07-01},
booktitle = {EDGE 2024},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
3604.
Yin, Jia; Wang, Wei; Guo, Zhonghua; Ji, Yangchun
DTS: dynamic training slimming with feature sparsity for efficient convolutional neural network Journal Article
In: Journal of Real-Time Image Processing, 2024.
@article{Yin-jrtip24a,
title = {DTS: dynamic training slimming with feature sparsity for efficient convolutional neural network},
author = {
Jia Yin and Wei Wang and Zhonghua Guo and Yangchun Ji
},
url = {https://link.springer.com/article/10.1007/s11554-024-01511-y},
year = {2024},
date = {2024-07-01},
urldate = {2024-07-01},
journal = { Journal of Real-Time Image Processing},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
3603.
(Ed.)
Neural Architecture Search for Adversarial Robustness via Learnable Pruning Collection
2024.
@collection{Li-fhpc24a,
title = {Neural Architecture Search for Adversarial Robustness via Learnable Pruning},
author = { Yize Li and Pu Zhao and Ruyi Ding and Tong Zhou and Yunsi Fei and Xiaolin Xu and Xue Lin },
url = {https://www.frontiersin.org/journals/high-performance-computing/articles/10.3389/fhpcp.2024.1301384/abstract},
year = {2024},
date = {2024-06-18},
urldate = {2024-06-18},
booktitle = {Frontiers in High Performance Computing},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
3602.
Yang, Jiechao; Liu, Yong
ETAS: Zero-Shot Transformer Architecture Search via Network Trainability and Expressivity Miscellaneous
2024.
@misc{Yang-24a,
title = {ETAS: Zero-Shot Transformer Architecture Search via Network Trainability and Expressivity},
author = {Jiechao Yang and Yong Liu },
url = {https://gsai.ruc.edu.cn/uploads/20240608/0d316f5c76e76d2d0a9ddc532a75be5d.pdf},
year = {2024},
date = {2024-06-18},
urldate = {2024-06-18},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
3601.
(Ed.)
UP-NAS: Unified Proxy for Neural Architecture Search Collection
2024.
@collection{Huang-cvprw24a,
title = {UP-NAS: Unified Proxy for Neural Architecture Search},
author = {Yi-Cheng Huang and Wei-Hua Li and Chih-Han Tsou and Jun-Cheng Chen and Chu-Song Chen},
url = {https://openaccess.thecvf.com/content/CVPR2024W/CVPR-NAS/papers/Huang_UP-NAS_Unified_Proxy_for_Neural_Architecture_Search_CVPRW_2024_paper.pdf},
year = {2024},
date = {2024-06-13},
urldate = {2024-06-13},
booktitle = {CVPR 2024 Workshop },
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
3600.
Wang, Xin; Chen, Hong; Pan, Zirui; Zhou, Yuwei; Guan, Chaoyu; Sun, Lifeng; Zhu, Wenwu
Automated Disentangled Sequential Recommendation with Large Language Models Journal Article
In: ACM Trans. Inf. Syst., 2024, ISSN: 1046-8188, (Just Accepted).
@article{10.1145/3675164,
title = {Automated Disentangled Sequential Recommendation with Large Language Models},
author = {Xin Wang and Hong Chen and Zirui Pan and Yuwei Zhou and Chaoyu Guan and Lifeng Sun and Wenwu Zhu},
url = {https://doi.org/10.1145/3675164},
doi = {10.1145/3675164},
issn = {1046-8188},
year = {2024},
date = {2024-06-01},
urldate = {2024-06-01},
journal = {ACM Trans. Inf. Syst.},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
abstract = {Sequential recommendation aims to recommend the next items that a target user may have interest in based on the user’s sequence of past behaviors, which has become a hot research topic in both academia and industry. In the literature, sequential recommendation adopts a Sequence-to-Item or Sequence-to-Sequence training strategy, which supervises a sequential model with a user’s next one or more behaviors as the labels and the sequence of the past behaviors as the input. However, existing powerful sequential recommendation approaches employ more and more complex deep structures such as Transformer in order to accurately capture the sequential patterns, which heavily rely on hand-crafted designs on key attention mechanism to achieve state-of-the-art performance, thus failing to automatically obtain the optimal design of attention representation architectures in various scenarios with different data. Other works on classic automated deep recommender systems only focus on traditional settings, ignoring the problem of sequential scenarios. In this paper, we study the problem of automated sequential recommendation, which faces two main challenges: i) How can we design a proper search space tailored for attention automation in sequential recommendation, and ii) How can we accurately search effective attention representation architectures considering multiple user interests reflected in the sequential behavior. To tackle these challenges, we propose an automated disentangled sequential recommendation (AutoDisenSeq) model. In particular, we employ neural architecture search (NAS) and design a search space tailored for automated attention representation in attentive intention-disentangled sequential recommendation with an expressive and efficient space complexity of (O(n^2)) given (n) as the number of layers. We further propose a context-aware parameter sharing mechanism taking characteristics of each sub-architecture into account to enable accurate architecture performance estimations and great flexibility for disentanglement of latent intention representation. Moreover, we propose AutoDisenSeq-LLM, which utilizes the textual understanding power of large language model (LLM) as a guidance to refine the candidate list for recommendation from AutoDisenSeq. We conduct extensive experiments to show that our proposed AutoDisenSeq model and AutoDisenSeq-LLM model outperform existing baseline methods on four real-world datasets in both overall recommendation and cold-start recommendation scenarios.},
note = {Just Accepted},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Sequential recommendation aims to recommend the next items that a target user may have interest in based on the user’s sequence of past behaviors, which has become a hot research topic in both academia and industry. In the literature, sequential recommendation adopts a Sequence-to-Item or Sequence-to-Sequence training strategy, which supervises a sequential model with a user’s next one or more behaviors as the labels and the sequence of the past behaviors as the input. However, existing powerful sequential recommendation approaches employ more and more complex deep structures such as Transformer in order to accurately capture the sequential patterns, which heavily rely on hand-crafted designs on key attention mechanism to achieve state-of-the-art performance, thus failing to automatically obtain the optimal design of attention representation architectures in various scenarios with different data. Other works on classic automated deep recommender systems only focus on traditional settings, ignoring the problem of sequential scenarios. In this paper, we study the problem of automated sequential recommendation, which faces two main challenges: i) How can we design a proper search space tailored for attention automation in sequential recommendation, and ii) How can we accurately search effective attention representation architectures considering multiple user interests reflected in the sequential behavior. To tackle these challenges, we propose an automated disentangled sequential recommendation (AutoDisenSeq) model. In particular, we employ neural architecture search (NAS) and design a search space tailored for automated attention representation in attentive intention-disentangled sequential recommendation with an expressive and efficient space complexity of (O(n^2)) given (n) as the number of layers. We further propose a context-aware parameter sharing mechanism taking characteristics of each sub-architecture into account to enable accurate architecture performance estimations and great flexibility for disentanglement of latent intention representation. Moreover, we propose AutoDisenSeq-LLM, which utilizes the textual understanding power of large language model (LLM) as a guidance to refine the candidate list for recommendation from AutoDisenSeq. We conduct extensive experiments to show that our proposed AutoDisenSeq model and AutoDisenSeq-LLM model outperform existing baseline methods on four real-world datasets in both overall recommendation and cold-start recommendation scenarios.
3599.
(Ed.)
On Efficient Object-Detection NAS for ADAS on Edge devices Collection
2024.
@collection{Gupta-CAI24a,
title = {On Efficient Object-Detection NAS for ADAS on Edge devices},
author = {Diksha Gupta and Rhui Dih Lee and Laura Wynter },
url = {https://ieeecai.org/2024/wp-content/pdfs/540900b013/540900b013.pdf},
year = {2024},
date = {2024-06-01},
urldate = {2024-06-01},
booktitle = {2024 IEEE Conference on Artificial Intelligence (CAI)},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
3598.
Micheal, A Ancy; Micheal, A Annie; Gopinathan, Anurekha; Barath, B U Anu
Deep Learning-based Multi-class Object Tracking With Occlusion Handling Mechanism in Uav Videos Technical Report
2024.
@techreport{nokey,
title = {Deep Learning-based Multi-class Object Tracking With Occlusion Handling Mechanism in Uav Videos},
author = {A Ancy Micheal and A Annie Micheal and Anurekha Gopinathan and B U Anu Barath},
url = {https://www.researchsquare.com/article/rs-4488926/v1},
year = {2024},
date = {2024-06-01},
urldate = {2024-06-01},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
3597.
(Ed.)
Disentangled Continual Graph Neural Architecture Search with Invariant Modular Supernet Collection
2024.
@collection{zhang-icml24a,
title = { Disentangled Continual Graph Neural Architecture Search with Invariant Modular Supernet },
author = { Zeyang Zhang and Xin Wang and Yijian Qin and Hong Chen and Ziwei Zhang and Xu Chu and Wenwu Zhu },
url = {http://mn.cs.tsinghua.edu.cn/xinwang/PDF/papers/2024_Disentangled%20Continual%20Graph%20Neural%20Architecture%20Search%20with%20Invariant%20Modular%20Supernet.pdf},
year = {2024},
date = {2024-06-01},
booktitle = {Proceedings of the 41 st International Conference on Machine Learning},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
3596.
Gao, Tianxiao; Guo, Li; Zhao, Shanwei; Xu, Peihan; Yang, Yukun; Liu, Xionghao; Wang, Shihao; Zhu, Shiai; Zhou, Dajiang
QuantNAS: Quantization-aware Neural Architecture Search For Efficient Deployment On Mobile Device Proceedings Article
In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 1704-1713, 2024.
@inproceedings{Gao_2024_CVPR,
title = {QuantNAS: Quantization-aware Neural Architecture Search For Efficient Deployment On Mobile Device},
author = {Tianxiao Gao and Li Guo and Shanwei Zhao and Peihan Xu and Yukun Yang and Xionghao Liu and Shihao Wang and Shiai Zhu and Dajiang Zhou},
url = {https://openaccess.thecvf.com/content/CVPR2024W/CVPR-NAS/html/Gao_QuantNAS_Quantization-aware_Neural_Architecture_Search_For_Efficient_Deployment_On_Mobile_CVPRW_2024_paper.html},
year = {2024},
date = {2024-06-01},
urldate = {2024-06-01},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
pages = {1704-1713},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
3595.
(Ed.)
Agent Based Model for AUTODL Optimisation Collection
2024.
@collection{Hedhili-icaart24a,
title = {Agent Based Model for AUTODL Optimisation},
author = {Aroua Hedhili and Imen Khelfa},
url = {https://www.scitepress.org/Papers/2024/123717/123717.pdf},
doi = {10.5220/0012371700003636},
year = {2024},
date = {2024-06-01},
urldate = {2024-06-01},
booktitle = {In Proceedings of the 16th International Conference on Agents and Artificial Intelligence (ICAART 2024) },
volume = {3},
pages = {568-575},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
3594.
Wang, Zixiao; Wang, Jiansu; Li, Shuo; Yang, Jiadi; Xing, Tianzhang
A lightweight and real-time responsive framework for various visual tasks via neural architecture search Journal Article
In: CCF Transactions on Pervasive Computing and Interaction , 2024.
@article{Wang-ccftpci24a,
title = {A lightweight and real-time responsive framework for various visual tasks via neural architecture search},
author = {Zixiao Wang and Jiansu Wang and Shuo Li and Jiadi Yang and Tianzhang Xing },
url = {https://link.springer.com/article/10.1007/s42486-024-00157-w},
year = {2024},
date = {2024-05-21},
urldate = {2024-05-21},
journal = {CCF Transactions on Pervasive Computing and Interaction },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
3593.
Krestinskaya, Olga; Fouda, Mohammed E.; Benmeziane, Hadjer; Maghraoui, Kaoutar El; Sebastian, Abu; Lu, Wei D.; Lanza, Mario; Li, Hai; Kurdahi, Fadi; Fahmy, Suhaib A.; Eltawil, Ahmed; Salama, Khaled N.
Neural architecture search for in-memory computing-based deep learning accelerators Journal Article
In: nature reviews electrical engineering , pp. 374-390, 2024.
@article{Krestinskaya-nree24a,
title = {Neural architecture search for in-memory computing-based deep learning accelerators},
author = {Olga Krestinskaya and Mohammed E. Fouda and Hadjer Benmeziane and Kaoutar El Maghraoui and Abu Sebastian and Wei D. Lu and Mario Lanza and Hai Li and Fadi Kurdahi and Suhaib A. Fahmy and Ahmed Eltawil and Khaled N. Salama
},
url = {https://www.nature.com/articles/s44287-024-00052-7},
year = {2024},
date = {2024-05-20},
urldate = {2024-05-20},
journal = {nature reviews electrical engineering },
pages = {374-390},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
3592.
Venske, Sandra Mara Scós; de Almeida, Carolina Paula; Delgado, Myriam Regattieri
Metaheuristics and machine learning: an approach with reinforcement learning assisting neural architecture search Journal Article
In: Journal of Heuristics, 2024.
@article{Venske-jh24a,
title = {Metaheuristics and machine learning: an approach with reinforcement learning assisting neural architecture search},
author = {
Sandra Mara Scós Venske and Carolina Paula de Almeida and Myriam Regattieri Delgado
},
url = {https://link.springer.com/article/10.1007/s10732-024-09526-1},
doi = {https://doi.org/10.1007/s10732-024-09526-1},
year = {2024},
date = {2024-05-16},
urldate = {2024-05-16},
journal = { Journal of Heuristics},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
3591.
Mengyan Jin Jianfang Cao, Yun Tian
Ancient mural dynasty recognition algorithm based on a neural network architecture search Journal Article
In: Heritage Science , 2024.
@article{cao-hs24a,
title = {Ancient mural dynasty recognition algorithm based on a neural network architecture search},
author = {
Jianfang Cao, Mengyan Jin, Yun Tian, Zhen Cao & Cunhe Peng
},
url = {https://link.springer.com/article/10.1186/s40494-024-01274-6},
year = {2024},
date = {2024-05-15},
urldate = {2024-05-15},
journal = {Heritage Science },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
3590.
Ray, Subhosit
TOWARDS SELF-ORGANIZED BRAIN: TOPOLOGICAL REINFORCEMENT LEARNING WITH GRAPH CELLULAR AUTOMATA PhD Thesis
2024.
@phdthesis{ray-phd24a,
title = {TOWARDS SELF-ORGANIZED BRAIN: TOPOLOGICAL REINFORCEMENT LEARNING WITH GRAPH CELLULAR AUTOMATA},
author = {Subhosit Ray},
url = {https://www.proquest.com/docview/3054372231?pq-origsite=gscholar&fromopenview=true&sourcetype=Dissertations%20&%20Theses},
year = {2024},
date = {2024-05-01},
urldate = {2024-05-01},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
3589.
Ramaraj, N.; Murugan, G.; Regunathan, R.
Neural Network-Powered Conductorless Ticketing for Public Transportation Proceedings Article
In: 2024 4th International Conference on Pervasive Computing and Social Networking (ICPCSN), pp. 236-241, IEEE Computer Society, Los Alamitos, CA, USA, 2024.
@inproceedings{10607626,
title = {Neural Network-Powered Conductorless Ticketing for Public Transportation},
author = {N. Ramaraj and G. Murugan and R. Regunathan},
url = {https://doi.ieeecomputersociety.org/10.1109/ICPCSN62568.2024.00047},
doi = {10.1109/ICPCSN62568.2024.00047},
year = {2024},
date = {2024-05-01},
urldate = {2024-05-01},
booktitle = {2024 4th International Conference on Pervasive Computing and Social Networking (ICPCSN)},
pages = {236-241},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {The efficient functioning of public transportation systems is pivotal for societal connectivity and economic progress, as they serve as lifelines for commuting and mobility. However, the dependency on manual ticketing processes often leads to bottlenecks and inefficiencies, hindering smooth operations and customer satisfaction. This research work focuses on developing an Automated Ticketing System for public transportation, utilizing Computer Vision and Neural Networks. Through the incorporation of Neural Architecture Search and the integration of Deep Sort, a Deep Learning-based object tracking model, with aim to enhance system efficiency. The study demonstrates promising results, indicating the potential for streamlined ticketing processes in public transportation.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The efficient functioning of public transportation systems is pivotal for societal connectivity and economic progress, as they serve as lifelines for commuting and mobility. However, the dependency on manual ticketing processes often leads to bottlenecks and inefficiencies, hindering smooth operations and customer satisfaction. This research work focuses on developing an Automated Ticketing System for public transportation, utilizing Computer Vision and Neural Networks. Through the incorporation of Neural Architecture Search and the integration of Deep Sort, a Deep Learning-based object tracking model, with aim to enhance system efficiency. The study demonstrates promising results, indicating the potential for streamlined ticketing processes in public transportation.
3588.
Porta, Alessandro Benfenati Ambra Catozzi Giorgia Franchini Federica
Early stopping strategies in Deep Image Prior Technical Report
2024.
@techreport{Benfenati-prep24a,
title = {Early stopping strategies in Deep Image Prior},
author = {Alessandro Benfenati Ambra Catozzi Giorgia Franchini Federica Porta},
url = {https://www.researchsquare.com/article/rs-4396753/v1},
year = {2024},
date = {2024-05-01},
urldate = {2024-05-01},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
3587.
Lee, Matthew; Sanchez-Matilla, Ricardo; Stoyanov, Danail; Luengo, Imanol
DIPO: Differentiable Parallel Operation Blocks for Surgical Neural Architecture Search Journal Article
In: IEEE J Biomed Health Inform , 2024.
@article{LeeIEEEJBHI24a,
title = { DIPO: Differentiable Parallel Operation Blocks for Surgical Neural Architecture Search },
author = {Matthew Lee and Ricardo Sanchez-Matilla and Danail Stoyanov and Imanol Luengo
},
url = {https://pubmed.ncbi.nlm.nih.gov/38805333/},
year = {2024},
date = {2024-05-01},
urldate = {2024-05-01},
journal = { IEEE J Biomed Health Inform },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
3586.
Li, Guilin; Wang, Qiang; Zheng, Xiawu
Distilling Structural Knowledge for Platform-Aware Semantic Segmentation Journal Article
In: Journal of Physics: Conference Series, vol. 2759, no. 1, pp. 012010, 2024.
@article{Li_2024,
title = {Distilling Structural Knowledge for Platform-Aware Semantic Segmentation},
author = {Guilin Li and Qiang Wang and Xiawu Zheng},
url = {https://dx.doi.org/10.1088/1742-6596/2759/1/012010},
doi = {10.1088/1742-6596/2759/1/012010},
year = {2024},
date = {2024-05-01},
urldate = {2024-05-01},
journal = {Journal of Physics: Conference Series},
volume = {2759},
number = {1},
pages = {012010},
publisher = {IOP Publishing},
abstract = {Knowledge Distillation (KD) aims to distill the dark knowledge of a high-powered teacher network into a student network, which can improve the capacity of student network and has been successfully applied to semantic segmentation. However, the standard knowledge distillation approaches merely represent the supervisory signal of teacher network as the dark knowledge, while ignoring the impact of network architecture during distillation. In this paper, we found that the student network with a more similar architecture against the teacher network obtains more performance gain from distillation. Therefore, a more generalized paradigm for knowledge distillation is to distill both the soft-label and the structure of the teacher network. We propose a novel Structural Distillation (SD) method which introduces the structural similarity constraints into vanilla knowledge distillation. We leverage Neural Architecture Search technique to search optimal student structure for semantic segmentation from a well-designed search space, which mimics the given teacher both in terms of soft-label and network structure. Experiment results make clear that our proposed method outperforms both the NAS with conventional Knowledge Distillation and human-designed methods, and achieves sota performance on the Cityscapes dataset under various platform-aware latency constraints. Furthermore, the best architecture discovered on Cityscapes also transfers well to the PASCAL VOC2012 dataset.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Knowledge Distillation (KD) aims to distill the dark knowledge of a high-powered teacher network into a student network, which can improve the capacity of student network and has been successfully applied to semantic segmentation. However, the standard knowledge distillation approaches merely represent the supervisory signal of teacher network as the dark knowledge, while ignoring the impact of network architecture during distillation. In this paper, we found that the student network with a more similar architecture against the teacher network obtains more performance gain from distillation. Therefore, a more generalized paradigm for knowledge distillation is to distill both the soft-label and the structure of the teacher network. We propose a novel Structural Distillation (SD) method which introduces the structural similarity constraints into vanilla knowledge distillation. We leverage Neural Architecture Search technique to search optimal student structure for semantic segmentation from a well-designed search space, which mimics the given teacher both in terms of soft-label and network structure. Experiment results make clear that our proposed method outperforms both the NAS with conventional Knowledge Distillation and human-designed methods, and achieves sota performance on the Cityscapes dataset under various platform-aware latency constraints. Furthermore, the best architecture discovered on Cityscapes also transfers well to the PASCAL VOC2012 dataset.