Feature Correlation-guided Knowledge Transfer for Federated Self-supervised Learning

TL;DR

This paper introduces FedFoA, a novel federated self-supervised learning framework that uses feature correlation for model aggregation, enabling effective knowledge transfer without assumptions like model homogeneity or public datasets.

Contribution

FedFoA is a general, model-agnostic method that leverages feature correlation for communication-efficient, privacy-preserving federated self-supervised learning, outperforming existing approaches.

Findings

FedFoA outperforms state-of-the-art methods significantly.

The relation matrix effectively captures semantic information.

FedFoA is compatible with various unsupervised FL methods.

Abstract

To eliminate the requirement of fully-labeled data for supervised model training in traditional Federated Learning (FL), extensive attention has been paid to the application of Self-supervised Learning (SSL) approaches on FL to tackle the label scarcity problem. Previous works on Federated SSL generally fall into two categories: parameter-based model aggregation (i.e., FedAvg, applicable to homogeneous cases) or data-based feature sharing (i.e., knowledge distillation, applicable to heterogeneous cases) to achieve knowledge transfer among multiple unlabeled clients. Despite the progress, all of them inevitably rely on some assumptions, such as homogeneous models or the existence of an additional public dataset, which hinder the universality of the training frameworks for more general scenarios. Therefore, in this paper, we propose a novel and general method named Federated Self-supervised Learning with Feature-correlation based Aggregation (FedFoA) to tackle the above limitations in a communication-efficient and privacy-preserving manner. Our insight is to utilize feature correlation to align the feature mappings and calibrate the local model updates across clients during their local training process. More specifically, we design a factorization-based method to extract the cross-feature relation matrix from the local representations. Then, the relation matrix can be regarded as a carrier of semantic information to perform the aggregation phase. We prove that FedFoA is a model-agnostic training framework and can be easily compatible with state-of-the-art unsupervised FL methods. Extensive empirical experiments demonstrate that our proposed approach outperforms the state-of-the-art methods by a significant margin.