Federated Learning (FL) aims at unburdening the training of deep models by distributing computation across multiple devices (clients) while safeguarding data privacy. On top of that, Federated Continual Learning (FCL) also accounts for data distribution evolving over time, mirroring the dynamic nature of real-world environments. While previous studies have identified Catastrophic Forgetting and Client Drift as major factors of performance degradation in FCL, we shed light on the importance of Incremental Bias and Federated Bias, which cause models to prioritize classes that are recently introduced or locally predominant, respectively. Our proposal constrains both biases to the last layer by efficiently fine-tuning a pre-trained backbone using learnable prompts, resulting in clients that produce less biased representations and more biased classifiers. Therefore, instead of solely relying on parameter aggregation, we leverage generative prototypes to effectively balance the predictions of the global model. Our proposed methodology significantly improves the current state of the art across six datasets, each including three different scenarios.
Federated Class-Incremental Learning with New-Class Augmented Self-Distillation
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Zhongguancun Laboratory（中关村实验室）；Beijing Jiaotong University（北京交通大学）
RefProtoFL: Communication-Efficient Federated Learning via External-Referenced Prototype Alignment
College of Intelligence and Computing, Tianjin University（智能与计算学院，天津大学）；State Key Lab. for Novel Software Technology, Nanjing University（新型软件技术国家重点实验室，南京大学）；Yunnan Key Lab. of Service Computing, Yunnan University of Finance and Economics（云南服务计算重点实验室，云南财经大学）
Personalized federated prototype learning in mixed heterogeneous data scenarios
Guangxi Normal University（广西师范大学）；Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, GuangXi Normal University（教育区块链与智能技术重点实验室）；Hefei University of Technology（合肥工业大学）
Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Northwestern University（西北大学）；University of Technology Sydney（悉尼科技大学）
Addressing Skewed Heterogeneity via Federated Prototype Rectification with Personalization
School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China（教育部新一代人工智能技术及其交叉应用重点实验室（东南大学））
Mitigating Domain Shift in Federated Learning via Intra- and Inter-Domain Prototypes
Department of Computer Science and Engineering, School of Computing, Kyung Hee University（计算机科学与工程系，计算学院，庆熙大学）；Department of Artificial Intelligence, School of Computing, Kyung Hee University（人工智能系，计算学院，庆熙大学）；Digital Science and Technology Institute, The University of Danang—Vietnam-Korea University of Information and Communication Technology（数字科学与技术研究所，丹那大学—越南-韩国信息与通信技术大学）
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）
Overcoming Catastrophic Forgetting in Federated Class-Incremental Learning via Federated Global Twin Generator
College of Engineering & Computer Science, VinUniversity（VinUniversity工程与计算机科学学院）；Vietnam National University - Ho Chi Minh city, University of Science（越南国家大学胡志明市分校自然科学大学）；Technische Universität Berlin（柏林工业大学）
Cross-Modal Prototype based Multimodal Federated Learning under Severely Missing Modality
Kyung Hee University（庆熙大学）；The University of Danang—Vietnam-Korea University of Information and Communication Technology（岘港大学—越韩信息与通信技术大学）；Digital Science and Technology Institute（数字科学技术研究院）
Taming Noise-Induced Prototype Degradation for Privacy-Preserving Personalized Federated Fine-Tuning
School of Artificial Intelligence, Beihang University（北京航空航天大学人工智能学院）；School of Statistics, Renmin University of China（中国人民大学统计学院）；School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）
Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learning
State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China（虚拟现实技术与系统国家重点实验室，计算机科学与工程学院，北京航空航天大学，北京，中国）；Zhongguancun Laboratory, Beijing, China（中关村实验室，北京，中国）；Center for AI Business Innovation, Department of Management Science and Systems, School of Management, University at Buffalo, USA（人工智能商业创新中心，管理科学与系统系，管理学院，布法罗大学，美国）
Robust Federated Learning on Edge Devices with Domain Heterogeneity
Department of Computer Science and Engineering, Kyung Hee University, 171-04, Republic of Korea（韩国庆熙大学计算机科学与工程系）；Machine learning department, Mohamed Bin Zayed University of Artificial Intelligence, United Arab Emirates（阿联酋穆罕默德·本·扎耶德人工智能大学机器学习系）
Prototype-Guided and Lightweight Adapters for Inherent Interpretation and Generalisation in Federated Learning
Hertie Institute for AI in Brain Health, University of Tübingen, Germany（人工智能与脑健康赫尔蒂研究所，图宾根大学，德国）；Tübingen AI Center, University of Tübingen, Germany（图宾根人工智能中心，图宾根大学，德国）
