Buffer-based Gradient Projection for Continual Federated Learning

TL;DR

This paper introduces Fed-A-GEM, a buffer-based gradient projection method for continual federated learning that reduces catastrophic forgetting by using local and aggregated buffer gradients, improving accuracy on benchmarks.

Contribution

It proposes Fed-A-GEM, a novel federated adaptation of A-GEM that leverages buffer-based gradient projection to mitigate forgetting without requiring task boundary knowledge.

Findings

Achieves up to 27% accuracy improvement on CIFAR-100.

Consistently outperforms existing CFL methods across benchmarks.

Effectively mitigates catastrophic forgetting in federated settings.

Abstract

Continual Federated Learning (CFL) is essential for enabling real-world applications where multiple decentralized clients adaptively learn from continuous data streams. A significant challenge in CFL is mitigating catastrophic forgetting, where models lose previously acquired knowledge when learning new information. Existing approaches often face difficulties due to the constraints of device storage capacities and the heterogeneous nature of data distributions among clients. While some CFL algorithms have addressed these challenges, they frequently rely on unrealistic assumptions about the availability of task boundaries (i.e., knowing when new tasks begin). To address these limitations, we introduce Fed-A-GEM, a federated adaptation of the A-GEM method (Chaudhry et al., 2019), which employs a buffer-based gradient projection approach. Fed-A-GEM alleviates catastrophic forgetting by leveraging local buffer samples and aggregated buffer gradients, thus preserving knowledge across multiple clients. Our method is combined with existing CFL techniques, enhancing their performance in the CFL context. Our experiments on standard benchmarks show consistent performance improvements across diverse scenarios. For example, in a task-incremental learning scenario using the CIFAR-100 dataset, our method can increase the accuracy by up to 27%. Our code is available at https://github.com/shenghongdai/Fed-A-GEM.