Early Exit Neural Networks (EENNs) present a solution to enhance the efficiency of neural network deployments. However, creating EENNs is challenging and requires specialized domain knowledge, due to the large amount of additional design choices. To address this issue, we propose an automated augmentation flow that focuses on converting an existing model into an EENN. It performs all required design decisions for the deployment to heterogeneous or distributed hardware targets: Our framework constructs the EENN architecture, maps its subgraphs to the hardware targets, and configures its decision mechanism. To the best of our knowledge, it is the first framework that is able to perform all of these steps.
We evaluated our approach on a collection of Internet-of-Things and standard image classification use cases. For a speech command detection task, our solution was able to reduce the mean operations per inference by 59.67%. For an ECG classification task, it was able to terminate all samples early, reducing the mean inference energy by 74.9% and computations by 78.3%. On CIFAR-10, our solution was able to achieve up to a 58.75% reduction in computations.
The search on a ResNet-152 base model for CIFAR-10 took less than nine hours on a laptop CPU. Our proposed approach enables the creation of EENN optimized for IoT environments and can reduce the inference cost of Deep Learning applications on embedded and fog platforms, while also significantly reducing the search cost - making it more accessible for scientists and engineers in industry and research. The low search cost improves the accessibility of EENNs, with the potential to improve the efficiency of neural networks in a wide range of practical applications.
An Efficient Unsupervised Federated Learning Approach for Anomaly Detection in Heterogeneous IoT Networks
Faculty of Electrical and Computer Engineering, Qom University of Technology(电气与计算机工程学院,科姆技术大学);Department of Computer Engineering, Faculty of Industry and Mining (Khash), Sistan and Baluchestan University(计算机工程系,工业与采矿学院(Khash),锡斯坦和巴尔赫斯坦大学);Canadian Institute for Cybersecurity, University of New Brunswick(加拿大网络安全研究所,新不伦瑞克大学);Sustainable Digitalisation Research Centre (SDRC), Department of Computer Science and Media Technology, Faculty of Technology and Society, Malmo University(可持续数字化研究中心(SDRC),计算机科学与媒体技术系,技术与社会学院,马尔默大学)
MMBind: Unleashing the Potential of Distributed and Heterogeneous Data for Multimodal Learning in IoT
Hong Kong University of Science and Technology(香港科技大学);University of California, Los Angeles(加州大学洛杉矶分校);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);U.S. Army DEVCOM Army Research Laboratory(美国陆军DEVCOM陆军研究实验室)
Federated Learning with Gramian Angular Fields for Privacy-Preserving ECG Classification on Heterogeneous IoT Devices
Laboratoire LITAN(LITAN实验室);École supérieure en Sciences et Technologies de l’Informatique et du Numérique(信息与数字技术高级学院);College of Engineering and IT(工程与信息技术学院);University of Dubai(迪拜大学);Department of Computer Science(计算机科学系);University of Sharjah(沙迦大学)
Heterogeneous Graph Contrastive Learning with Spectral Augmentation
School of Cyber Science and Engineering, Southeast University(东南大学网络空间安全学院);School of Computer Science and Engineering, Nanjing University of Science and Technology(南京理工大学计算机科学与工程学院)
COMSPLIT: A Communication-Aware Split Learning Design for Heterogeneous IoT Platforms
Faculty of Technical Sciences, University of Novi Sad(诺维萨德大学技术科学学院);Institute for Artificial Intelligence Research and Development of Serbia(塞尔维亚人工智能研究与发展研究所);Science, Technology and Innovation Unit, The Abdus Salam International Centre for Theoretical Physics(阿卜杜勒·萨拉姆国际理论物理中心科学、技术与创新部)
Knowledge-Enhanced Semi-Supervised Federated Learning for Aggregating Heterogeneous Lightweight Clients in IoT
Pennsylvania State University(宾夕法尼亚州立大学);University of Electronic Science and Technology of China(电子科技大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Purdue University(普渡大学);Georgia State University(佐治亚州立大学)
XAI-SOH-FL: Enhancing SOH-FL with Adaptive Aggregation and Explainable AI for Intrusion Detection in Heterogeneous IoT
School of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology (NUST)(电气工程与计算机科学学院(SEECS),国家 sciences and Technology(NUST))
THeGAU: Type-Aware Heterogeneous Graph Autoencoder and Augmentation
Data Science Degree Program National Taiwan University;Graduate Institute of Communication Engineering National Taiwan University Taipei Taiwan;University of Illinois Urbana-Champaign Electrical \& Computer Engineering Illinois United States;Research Center for Information Technology Innovation Academia Sinica Taipei Taiwan;Department of Electrical Engineering National Taiwan University Taipei Taiwan;National Taiwan University;University of Illinois Urbana-Champaign
Adaptive Bi-Recommendation and Self-Improving Network for Heterogeneous Domain Adaptation-Assisted IoT Intrusion Detection
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);University of Chinese Academy of Sciences(中国科学院大学);University of Macau(澳门大学);University of New Brunswick(新不伦瑞克大学)
Generative AI-Powered Plugin for Robust Federated Learning in Heterogeneous IoT Networks
Institute of Information & Communications Technology Planning & Evaluation (IITP)-ITRC (Information Technology Research Center)(信息与通信技术规划与评估院(IITP)-ITRC(信息技术研究中心))
Federated Knowledge Transfer Fine-tuning Large Server Model with Resource-Constrained IoT Clients
School of Intelligent Systems Engineering, Sun Yat-Sen University(中山大学智能工程学院);Shenzhen Fangle Technology Co., Ltd.(深圳方乐科技有限公司);School of Computer Science and Engineering, Nanyang Technological University(南洋理工大学计算机科学与工程学院);School of Computer Science and Technology, Dalian University of Technology(大连理工大学计算机科学与技术学院);School of Electronic Engineering and Computer Science, Queen Mary University of London(伦敦玛丽女王大学电子工程与计算机科学学院)
Heterogeneous Domain Adaptation for IoT Intrusion Detection: A Geometric Graph Alignment Approach
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);University of Chinese Academy of Sciences(中国科学院大学);University of Macau(澳门大学)
SegHeD+: Segmentation of Heterogeneous Data for Multiple Sclerosis Lesions with Anatomical Constraints and Lesion-aware Augmentation
Imperial College London(帝国理工学院);Data Science Institute, Imperial College London(帝国理工学院数据科学研究所);UK Dementia Research Institute, Imperial College London(帝国理工学院英国痴呆症研究所);Rosalind Franklin Institute(罗莎琳德·富兰克林研究所)
School of Computer Science and Technology, Anhui University(安徽大学计算机科学与技术学院);Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China), Hefei University of Technology(大数据知识工程重点实验室(教育部))