Learn from Others and Be Yourself in Heterogeneous Federated Learning
Authors:
Top Cited Papers
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 10133-10143
Abstract
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 CrossCorrelation 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. Mean- while, 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.Keywords
Funding Information
- National Natural Science Foundation of China (62176188,62141112,41871243)
This publication has 32 references indexed in Scilit:
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016
- Unsupervised Visual Representation Learning by Context Prediction2015
- Going deeper with convolutions2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Model compression2006
- A Tutorial on the Cross-Entropy MethodAnnals of Operations Research, 2005
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- A database for handwritten text recognition researchIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994
- Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem1989
- On Information and SufficiencyThe Annals of Mathematical Statistics, 1951