As Internet of Things (IoT) technology advances, end devices like sensors and smartphones are progressively equipped with AI models tailored to their local memory and computational constraints. Local inference reduces communication costs and latency; however, these smaller models typically underperform compared to more sophisticated models deployed on edge servers or in the cloud. Cooperative Inference Systems (CISs) address this performance trade-off by enabling smaller devices to offload part of their inference tasks to more capable devices. These systems often deploy hierarchical models that share numerous parameters, exemplified by Deep Neural Networks (DNNs) that utilize strategies like early exits or ordered dropout. In such instances, Federated Learning (FL) may be employed to jointly train the models within a CIS. Yet, traditional training methods have overlooked the operational dynamics of CISs during inference, particularly the potential high heterogeneity in serving rates across clients. To address this gap, we propose a novel FL approach designed explicitly for use in CISs that accounts for these variations in serving rates. Our framework not only offers rigorous theoretical guarantees, but also surpasses state-of-the-art (SOTA) training algorithms for CISs, especially in scenarios where inference request rates or data availability are uneven among clients.
Federated Inference: Toward Privacy-Preserving Collaborative and Incentivized Model Serving
Department of Electrical Engineering and Computer Science, University of Stavanger(电子工程与计算机科学系,斯塔万格大学);Department of Data Science, The Catholic University of Korea(数据科学系,韩国天主大学)
Towards Collaborative Fairness in Federated Learning Under Imbalanced Covariate Shift
The Pennsylvania State University(宾夕法尼亚州立大学);State University of New York at Albany(纽约州立大学阿尔巴尼分校);University of Minnesota Twin Cities(明尼苏达大学双城分校);Dalian University of Technology(大连理工大学)
FedAGHN: Personalized Federated Learning with Attentive Graph HyperNetworks
Tsinghua University(清华大学);Fuyao University of Science and Technology(福耀科技大学);Hong Kong University of Science and Technology(香港科技大学);Shenzhen University(深圳大学);Southern University of Science and Technology(南方科技大学)
A Novel Collaborative Framework for Efficient Synchronization in Split Federated Learning over Wireless Networks
Department of Electrical and Computer Engineering, Concordia University(电气与计算机工程系,康科迪亚大学);Department of Physics and Computer Science, Faculty of Science, Wilfrid Laurier University(物理与计算机科学系,科学学院,威尔弗里德·劳里埃大学)
Federated Hierarchical Tensor Networks: a Collaborative Learning Quantum AI-Driven Framework for Healthcare
Purdue University(普渡大学);Davidson School of Chemical Engineering(戴维森化学工程学院);Research Institute for Advanced Computer Science(高级计算机科学研究所);Universities Space Research Association(大学空间研究协会);NASA Ames Research Center(美国国家航空航天局艾姆斯研究中心)
Blockchain Federated Learning for Sustainable Retail: Reducing Waste through Collaborative Demand Forecasting
DISMI, University of Modena and Reggio Emilia(DISMI,Modena和Reggio Emilia大学);En\&Tech, University of Modena and Reggio Emilia(En\&Tech,Modena和Reggio Emilia大学);DIN, University of Bologna(DIN,博洛尼亚大学)
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。
Federated Learning via Input-Output Collaborative Distillation
University at Buffalo(布法罗大学);Institute of Artificial Intelligence, Beihang University(北京航空航天大学人工智能研究院);Harvard Medical School(哈佛医学院);Virginia Tech(弗吉尼亚理工大学);Jarvis Research Center, Tencent YouTu Lab(腾讯优图实验室杰瑞斯研究中心);United Imaging Intelligence(联影智能);Hangzhou Research Institute, Beihang University(北京航空航天大学杭州研究院);Zhongguancun Laboratory(中关村实验室);Nanchang Institute of Technology(南昌工学院)
Semantic Communication in Dynamic Channel Scenarios: Collaborative Optimization of Dual-Pipeline Joint Source-Channel Coding and Personalized Federated Learning
Beijing Institute of Technology(北京理工大学);Institute of Computer Application Technology Norinco Groups(中国兵器工业集团计算机应用技术研究所)
Privacy-Preserving Asynchronous Federated Learning Algorithms for Multi-Party Vertically Collaborative Learning
JD Finance America Corporation(京东金融美国公司);Department of Electrical & Computer Engineering, University of Pittsburgh(匹兹堡大学电气与计算机工程系);University of Pittsburgh(匹兹堡大学)
FedPall: Prototype-based Adversarial and Collaborative Learning for Federated Learning with Feature Drift
Artificial Intelligence Research Institute, Shenzhen MSU-BIT University(深圳MSU-BIT大学人工智能研究院);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究所);School of Medical Technology, Beijing Institute of Technology(北京理工大学医学技术学院)
User profile-driven large-scale multi-agent learning from demonstration in federated human-robot collaborative environments
Institute of Computer Science (ICS), Foundation for Research and Technology - Hellas (FORTH)(计算机科学研究所,研究与技术基金会-希腊);Computer Science Department (CSD), University of Crete (UoC)(克里特大学计算机科学系)