Learn From Others and Be Yourself in Heterogeneous Federated Learning
Federated learning has emerged as an important distributed learning paradigm, which normally involves collaborative updating with others and local updating on private data. However, heterogeneity problem and catastrophic forgetting bring distinctive challenges. First, due to non-i.i.d (identically and independently distributed) data and heterogeneous architectures, models suffer performance degradation on other domains and communication barrier with participants models. Second, in local updating, model is separately optimized on private data, which is prone to overfit current data distribution and forgets previously acquired knowledge, resulting in catastrophic forgetting. In this work, we propose FCCL (Federated Cross-Correlation and Continual Learning). For heterogeneity problem, FCCL leverages unlabeled public data for communication and construct cross-correlation matrix to learn a generalizable representation under domain shift. Meanwhile, for catastrophic forgetting, FCCL utilizes knowledge distillation in local updating, providing inter and intra domain information without leaking privacy. Empirical results on various image classification tasks demonstrate the effectiveness of our method and the efficiency of modules.
Code (1)
Tasks
Continual LearningFederated Learningimage-classificationImage ClassificationKnowledge DistillationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Robust Heterogeneous Federated Learning under Data Corruption
Model heterogeneous federated learning is a realistic and challenging problem. However, due to the limitations of data collection, storage, and transmission conditions, as well as the existence of free-rider particip…
Data AugmentationFederated LearningTransfer LearningFedAL: Black-Box Federated Knowledge Distillation Enabled by Adversarial Learning
Knowledge distillation (KD) can enable collaborative learning among distributed clients that have different model architectures and do not share their local data and model parameters with others. Each client updates its …
Knowledge DistillationTransfer LearningGeneralizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learning
Federated learning is an important privacy-preserving multi-party learning paradigm, involving collaborative learning with others and local updating on private data. Model heterogeneity and catastrophic forgetting are tw…
Domain GeneralizationFederated LearningPrivacy PreservingInfluence-oriented Personalized Federated Learning
Traditional federated learning (FL) methods often rely on fixed weighting for parameter aggregation, neglecting the mutual influence by others. Hence, their effectiveness in heterogeneous data contexts is limited. To add…
Federated LearningPersonalized Federated LearningFeDa4Fair: Client-Level Federated Datasets for Fairness Evaluation
Federated Learning (FL) enables collaborative model training across multiple clients without sharing clients' private data. However, fairness remains a key concern, as biases in local clients' datasets can impact the ent…
AttributeBenchmarkingFairnessFederated Learning