Split Computing (SC), where a Deep Neural Network (DNN) is intelligently split with a part of it deployed on an edge device and the rest on a remote server is emerging as a promising approach. It allows the power of DNNs to be leveraged for latency-sensitive applications that do not allow the entire DNN to be deployed remotely, while not having sufficient computation bandwidth available locally. In many such embedded systems scenarios, such as those in the automotive domain, computational resource constraints also necessitate Multi-Task Learning (MTL), where the same DNN is used for multiple inference tasks instead of having dedicated DNNs for each task, which would need more computing bandwidth. However, how to partition such a multi-tasking DNN to be deployed within a SC framework has not been sufficiently studied. This paper studies this problem, and MTL-Split, our novel proposed architecture, shows encouraging results on both synthetic and real-world data. The source code is available at https://github.com/intelligolabs/MTL-Split.
Location-Centered House Price Prediction: A Multi-Task Learning Approach
Nanjing University of Science and Technology(南京理工大学);RMIT University(皇家墨尔本理工大学);Nanjing University of Finance and Economics(南京财经大学);Swinburne University of Technology(斯威本科技大学)
Combined Federated and Split Learning in Edge Computing for Ubiquitous Intelligence in Internet of Things: State of the Art and Future Directions
Pennsylvania State University(宾夕法尼亚州立大学);Fudan University(复旦大学)
联合学习(Federated Learning,FL)和分裂学习(Split Learning,SL)是两种新兴的协作学习方法,可以极大地促进物联网(Internet of Things,IoT)中的泛在智能。联邦学习使使用私有数据本地训练的机器学习(ML)模型能够聚合成全局模型。拆分学习允许ML模型的不同部分在学习框架中的不同工作者上进行协作训练。联邦学习和分裂学习各有其独特的优势和各自的局限性,可以相互补充,共同实现物联网中的泛在智能。因此,联邦学习和分裂学习的结合成为近年来一个活跃的研究领域,引起了广泛的兴趣。在本文中,我们回顾了联邦学习和分离学习的最新发展,并对在基于边缘计算的物联网环境中结合这两种学习方法的最新技术进行了调查。我们还确定了一些开放的问题,并讨论了在这一领域的未来研究的可能方向,希望进一步引起研究界对这一新兴领域的兴趣。
JASPER: Special Session on Joint Reliability And Security Assessment of SPlit Computing for Edge Robustness
Politecnico di Torino(都灵理工大学);Tallinn University of Technology(塔林理工大学);University of California, Irvine(加州大学欧文分校);Brandenburg University of Technology(勃兰登堡工业大学);Humboldt University of Berlin(柏林洪堡大学)
HASFL: Heterogeneity-aware Split Federated Learning over Edge Computing Systems
Department of Electrical and Electronic Engineering, University of Hong Kong(香港大学电子与电气工程系);Institute of Space Internet, Fudan University(复旦大学空间互联网研究所);School of Computer Science, Fudan University(复旦大学计算机科学学院)
GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems
Department of Electrical and Electronic Engineering, University of Hong Kong(香港大学电子与电气工程系);Data61, CSIRO(CSIRO数据61);Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg(卢森堡大学安全、可靠与信任跨学科中心)
Memory- and Latency-Constrained Inference of Large Language Models via Adaptive Split Computing
Department of Artificial Intelligence, Kyungpook National University(人工智能系,庆北国立大学);Department of Electrical and Computer Engineering, Queen’s University(电气与计算机工程系,皇后大学);Department of Information and Communications Engineering, Pukyong National University(信息与通信工程系,浦项国立大学)
Adaptive and Parallel Split Federated Learning in Vehicular Edge Computing
School of Computer Science and Engineering, University of Electronic Science and Technology of China(电子科技大学计算机科学与工程学院);Xidian University(西安电子科技大学);Guangzhou Institute of Technology, Xidian University(西安电子科技大学广州研究院);Faculty of Information Technology, University of Jyväskylä(于韦斯屈莱大学信息技术学院)
Neuromorphic Wireless Split Computing with Multi-Level Spikes
King’s Laboratory for Intelligent Computing (KLIC) lab within the Centre for Intelligent Information Processing Systems (CIIPS) at the Department of Engineering, King’s College London(国王智能计算实验室(KLIC)内位于智能信息处理系统中心(CIIPS)的工程系,伦敦国王学院);King’s Communications, Learning and Information Processing (KCLIP) lab within the CIIPS at the Department of Engineering, King’s College London(国王通讯、学习和信息处理(KCLIP)实验室,位于智能信息处理系统中心(CIIPS)的工程系,伦敦国王学院);Department of Electrical and Computer Engineering, Princeton University(普林斯顿大学电气与计算机工程系)
Neuromorphic Wireless Split Computing with Resonate-and-Fire Neurons
Department of Engineering, King’s College London(工程系,伦敦国王学院);Department of Electrical and Computer Engineering, Princeton University(电气与计算机工程系,普林斯顿大学);Institute for Intelligent Networked Systems, Northeastern University London(智能网络化系统研究所,伦敦东北大学)
SplitBeam: Effective and Efficient Beamforming in Wi-Fi Networks Through Split Computing
Donald Bren School of Information and Computer Sciences, University of California at Irvine(加州大学欧文分校唐纳德·布伦信息与计算机科学学院);Institute for the Wireless Internet of Things, Northeastern University(东北大学无线物联网研究所)
HSplitLoRA: A Heterogeneous Split Parameter-Efficient Fine-Tuning Framework for Large Language Models
Institute of Space Internet, Fudan University(复旦大学空间互联网研究所);School of Computer Science, Fudan University(复旦大学计算机科学学院);Department of Electrical and Electronic Engineering, University of Hong Kong(香港大学电子与电气工程系);Mohamed bin Zayed University of Artificial Intelligence(莫扎伊德人工智能大学);Massachusetts Institute of Technology(麻省理工学院);Data61, CSIRO(CSIRO Data61);School of Computer Engineering, Nanyang Technological University(南洋理工大学计算机工程学院)