Federated Unsupervised Representation Learning

TL;DR

This paper introduces Federated Unsupervised Representation Learning (FURL), a new approach for learning shared data representations across distributed edge devices without labels, addressing data heterogeneity and alignment challenges.

Contribution

It proposes the FedCA algorithm, combining dictionary aggregation and alignment modules to improve representation consistency and alignment in federated unsupervised learning.

Findings

FedCA outperforms baseline methods significantly.

Effective handling of Non-IID data distributions.

Improved representation alignment across clients.

Abstract

To leverage enormous unlabeled data on distributed edge devices, we formulate a new problem in federated learning called Federated Unsupervised Representation Learning (FURL) to learn a common representation model without supervision while preserving data privacy. FURL poses two new challenges: (1) data distribution shift (Non-IID distribution) among clients would make local models focus on different categories, leading to the inconsistency of representation spaces. (2) without the unified information among clients in FURL, the representations across clients would be misaligned. To address these challenges, we propose Federated Constrastive Averaging with dictionary and alignment (FedCA) algorithm. FedCA is composed of two key modules: (1) dictionary module to aggregate the representations of samples from each client and share with all clients for consistency of representation space and (2) alignment module to align the representation of each client on a base model trained on a public data. We adopt the contrastive loss for local model training. Through extensive experiments with three evaluation protocols in IID and Non-IID settings, we demonstrate that FedCA outperforms all baselines with significant margins.