With the fast evolvement of embedded deep-learning computing systems, applications powered by deep learning are moving from the cloud to the edge. When deploying neural networks (NNs) onto the devices under complex environments, there are various types of possible faults: soft errors caused by cosmic radiation and radioactive impurities, voltage instability, aging, temperature variations, and malicious attackers. Thus the safety risk of deploying NNs is now drawing much attention. In this paper, after the analysis of the possible faults in various types of NN accelerators, we formalize and implement various fault models from the algorithmic perspective. We propose Fault-Tolerant Neural Architecture Search (FT-NAS) to automatically discover convolutional neural network (CNN) architectures that are reliable to various faults in nowadays devices. Then we incorporate fault-tolerant training (FTT) in the search process to achieve better results, which is referred to as FTT-NAS. Experiments on CIFAR-10 show that the discovered architectures outperform other manually designed baseline architectures significantly, with comparable or fewer floating-point operations (FLOPs) and parameters. Specifically, with the same fault settings, F-FTT-Net discovered under the feature fault model achieves an accuracy of 86.2% (VS. 68.1% achieved by MobileNet-V2), and W-FTT-Net discovered under the weight fault model achieves an accuracy of 69.6% (VS. 60.8% achieved by ResNet-20). By inspecting the discovered architectures, we find that the operation primitives, the weight quantization range, the capacity of the model, and the connection pattern have influences on the fault resilience capability of NN models.
AutoShrink: A Topology-aware NAS for Discovering Efficient Neural Architecture
Duke University（杜克大学）；Peking University（北京大学）；University of Nevada, Reno（内华达大学雷诺分校）；Tsinghua University（清华大学）；ECE Department, Duke University（杜克大学电气与计算机工程系）；Institute of Computational Linguistics, Peking University（北京大学计算语言学研究所）；CSE Department, University of Nevada, Reno（内华达大学雷诺分校计算机科学与工程系）；Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）
Discovering Sparse Recovery Algorithms Using Neural Architecture Search
Computer Engineering New York University New York, USA（计算机工程 新 York 大学 新 York 美国）；Computer Engineering University of California, Riverside Riverside, USA（计算机工程 加州大学河滨分校 河滨 美国）；Tandon School of Engineering New York University New York, USA（Tandon 工程学院 新 York 大学 新 York 美国）
TG-NAS: Generalizable Zero-Cost Proxies with Operator Description Embedding and Graph Learning for Efficient Neural Architecture Search
Department of EECS, University of California, Irvine（电子工程与计算机科学系，加州大学伊市分校）；Department of Computer Science, University of California, San Diego（计算机科学系，加州大学圣地亚哥分校）
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）
DASViT: Differentiable Architecture Search for Vision Transformer
School of Computer Science and Electronic Engineering University of Surrey（计算机科学与电子工程学院大学 Surrey 大学）；School of Artificial Intelligence and Computer Science Jiangnan University（人工智能与计算机科学学院江南大学）
BioArc: Discovering Optimal Neural Architectures for Biological Foundation Models
Department of Computer Science, Virginia Tech, Blacksburg, VA, USA（弗吉尼亚理工学院计算机科学系）；Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA, USA（弗吉尼亚理工学院电气与计算机工程系）；Department of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA（卡内基梅隆大学计算机科学系）；Department of Biomedical Data Science, Stanford University, Stanford, CA, USA（斯坦福大学生物医学数据科学系）
Evolutionary Architecture Search through Grammar-Based Sequence Alignment
Carlos III University of Madrid（马德里卡洛斯三世大学）；University of Edinburgh（爱丁堡大学）；Instituto de Investigación Sanitaria Gregorio Marañón（Gregorio Marañón卫生研究院）；Helmholtz-Zentrum Berlin für Materialien und Energie（柏林材料与能源研究中心）；ELLIS Institute Tübingen（图宾根ELLIS研究所）；University of Glasgow（格拉斯哥大学）
emoDARTS: Joint Optimisation of CNN & Sequential Neural Network Architectures for Superior Speech Emotion Recognition
University of Southern Queensland（南昆士兰大学）；Queensland University of Technology（昆士兰科技大学）；The University of Texas at Dallas（德克萨斯大学达拉斯分校）；Technical University of Munich（慕尼黑工业大学）；Munich Data Science Institute（慕尼黑数据科学研究所）；Munich Center for Machine Learning（慕尼黑机器学习中心）；Imperial College London（帝国理工学院）
University of California San Diego（加州大学圣地亚哥分校）；ETH Zurich（苏黎世联邦理工学院）；Fermi National Accelerator Laboratory（费米国家加速器实验室）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）
