Standard federated learning approaches suffer when client data distributions have sufficient heterogeneity. Recent methods addressed the client data heterogeneity issue via personalized federated learning (PFL) - a class of FL algorithms aiming to personalize learned global knowledge to better suit the clients' local data distributions. Existing PFL methods usually decouple global updates in deep neural networks by performing personalization on particular layers (i.e. classifier heads) and global aggregation for the rest of the network. However, preselecting network layers for personalization may result in suboptimal storage of global knowledge. In this work, we propose FedSelect, a novel PFL algorithm inspired by the iterative subnetwork discovery procedure used for the Lottery Ticket Hypothesis. FedSelect incrementally expands subnetworks to personalize client parameters, concurrently conducting global aggregations on the remaining parameters. This approach enables the personalization of both client parameters and subnetwork structure during the training process. Finally, we show that FedSelect outperforms recent state-of-the-art PFL algorithms under challenging client data heterogeneity settings and demonstrates robustness to various real-world distributional shifts. Our code is available at https://github.com/lapisrocks/fedselect.
Towards Optimal Customized Architecture for Heterogeneous Federated Learning with Contrastive Cloud-Edge Model Decoupling
Southwestern University of Finance and Economics（西南财经大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；City University of Hong Kong（香港城市大学）
Personalized Federated Learning for Spatio-Temporal Forecasting: A Dual Semantic Alignment-Based Contrastive Approach
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
City University of Hong Kong（香港城市大学）；Hong Kong Metropolitan University（香港 Metropolitan 大学）；Xi’an Jiaotong University（西安交通大学）；Southeast University（东南大学）；Jinan University（吉林大学）；CityU Shenzhen Research Institute（城大深圳研究院）
Fusion of Global and Local Knowledge for Personalized Federated Learning
Georgia Institute of Technology（佐治亚理工学院）；JD Explore Academy（京东探索研究院）；The University of Sydney（悉尼大学）；South China University of Technology（华南理工大学）；Peng Cheng Laboratory（鹏城实验室）
School of Cyber Engineering, Xidian University（西安电子科技大学电子工程学院）；Chinese Academy of Sciences（中国科学院）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；Cyberspace Institute of Advanced Technology, Guangzhou University（广州大学空天信息研究院）
Personalized Federated Learning on Heterogeneous and Long-Tailed Data via Expert Collaborative Learning
Xiamen University（厦门大学）；University College London（伦敦大学学院）；A*STAR Institute of High Performance Computing（新加坡高性能计算研究院）；Guangdong University of Technology（广东工业大学）；Guangdong Laboratory of Artificial Intelligence and Digital Economy（广东省人工智能与数字经济实验室）
Investigation of Customized Medical Decision Algorithms Utilizing Graph Neural Networks
Stevens Institute of Technology（史蒂文斯理工学院）；Northeastern University（东北大学）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Brandeis University（布兰迪斯大学）；Carnegie Mellon University（卡内基梅隆大学）
Lorica: A Synergistic Fine-Tuning Framework for Advancing Personalized Adversarial Robustness
School of Cyber Science and Technology, Sun Yat-sen University（中山大学信息科学与技术学院）；School of Automation, Beijing Institute of Technology（北京理工大学自动化学院）；School of Cyber Science and Engineering, Xi’an Jiaotong University（西安交通大学网络安全工程学院）
