Personalized federated learning (PFL) studies effective model personalization to address the data heterogeneity issue among clients in traditional federated learning (FL). Existing PFL approaches mainly generate personalized models by relying solely on the clients' latest updated models while ignoring their previous updates, which may result in suboptimal personalized model learning. To bridge this gap, we propose a novel framework termed pFedSeq, designed for personalizing adapters to fine-tune a foundation model in FL. In pFedSeq, the server maintains and trains a sequential learner, which processes a sequence of past adapter updates from clients and generates calibrations for personalized adapters. To effectively capture the cross-client and cross-step relations hidden in previous updates and generate high-performing personalized adapters, pFedSeq adopts the powerful selective state space model (SSM) as the architecture of sequential learner. Through extensive experiments on four public benchmark datasets, we demonstrate the superiority of pFedSeq over state-of-the-art PFL methods.
Personalized Federated Sparse Adaptation of Time-Series Foundation Models
Robert Bosch Centre for Cyber-Physical Systems, Indian Institute of Science（罗伯特·博世网络物理系统中心，印度科学学院）；School of Computing, Newcastle University（纽卡斯尔大学计算学院）
Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing
Chandar Research Lab（Chandar研究实验室）；Mila – Quebec AI Institute（魁北克AI研究所）；Université de Montréal（蒙特利尔大学）；Microsoft Research（微软研究院）；Polytechnique Montréal（蒙特利尔理工学院）；Canada CIFAR AI Chair（加拿大CIFAR人工智能主席）
Parameter-Efficient and Personalized Federated Training of Generative Models at the Edge
Department of Computer Science, San Francisco State University（计算机科学系，圣弗朗西斯科州立大学）；Department of Communication Systems, University of Lakhimpur（通信系统系，拉贾斯坦邦大学）；Department of Embedded Systems, Manipur University（嵌入式系统系，曼尼普尔大学）；Department of Chemical Engineering, Lakshadweep University（化学工程系，拉克沙德韦普大学）
FedPDPO: Federated Personalized Direct Preference Optimization for Large Language Model Alignment
College of Intelligence and Computing, Tianjin University, Tianjin, China（智能与计算学院，天津大学，天津，中国）；College of Computing and Data Science, Nanyang Technological University, Singapore（计算与数据科学学院，南洋理工大学，新加坡）
Harnessing Data from Clustered LQR Systems: Personalized and Collaborative Policy Optimization
Department of Electrical and Computer Engineering（电气与计算机工程系）；North Carolina State University（北卡罗来纳州立大学）；The Elmore Family School of Electrical and Computer Engineering（埃尔莫尔家族电气与计算机工程学院）；Purdue University（普渡大学）
The Helicobacter pylori AI-Clinician: Harnessing Artificial Intelligence to Personalize H. pylori Treatment Recommendations
Imperial College London（帝国理工学院）；Hospital Universitario de La Princesa（拉普林塞萨大学医院）；Instituto de Investigación Sanitaria Princesa (IIS-Princesa)（普林塞萨健康研究所（IIS-Princesa））；Universidad Autónoma de Madrid (UAM)（马德里自治大学（UAM））；Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas (CIBEREHD)（肝脏与消化系统疾病生物医学研究网络中心（CIBEREHD））；Instituto Investigación Sanitaria INCLIVA (INCLIVA)（INCLIVA健康研究所（INCLIVA））；CIBERONC（CIBERONC癌症生物医学研究网络中心）；Hospital Clínico Universitario de Valencia（瓦伦西亚大学临床医院）；Universitat de Valencia（瓦伦西亚大学）；Yale University（耶鲁大学）
FedMCP: Parameter-Efficient Federated Learning with Model-Contrastive Personalization
School of Data Science and Engineering, East China Normal University（华东师范大学数据科学与工程学院）；Manning College of Information & Computer Sciences, University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校曼宁信息与计算机科学学院）
Pilot: Building the Federated Multimodal Instruction Tuning Framework
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Pengcheng Laboratory（鹏城实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS)（中国科学院大学人工智能学院）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
PFAdapter: Hierarchical LoRA Decomposition for Personalized Federated MLLMs
College of Future Information Technology, Fudan University（复旦大学未来信息技术学院）；Division of Natural and Applied Sciences, Duke Kunshan University（昆山杜克大学自然科学与应用科学部）；Department of Electrical and Computer Engineering, The University of British Columbia（英属哥伦比亚大学电气与计算机工程系）；Ant Group（蚂蚁集团）；College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）；School of Data Science and Engineering, East China Normal University（华东师范大学数据科学与工程学院）；College of Intelligent Robotics and Advanced Manufacturing, Fudan University & Fysics AI（复旦大学智能机器人与先进制造学院及复肆智能科技（上海）有限公司）；Xiaomi EV, Xiaomi Campus（小米汽车、小米园区）；Information and Communications Technology Cluster, Singapore Institute of Technology (SIT)（新加坡理工学院信息通信技术集群）；College of Electronic and Information Engineering, Tongji University（同济大学电子与信息工程学院）；School of Computer Science and Informatics, Cardiff University（卡迪夫大学计算机科学与信息学院）
