FedMeS: Personalized Federated Continual Learning Leveraging Local Memory

TL;DR

FedMeS introduces a personalized federated continual learning framework that uses local memory and Gaussian inference to mitigate client drift and catastrophic forgetting, achieving superior accuracy and retention across diverse tasks.

Contribution

The paper presents FedMeS, a novel PFCL framework that leverages local memory and Gaussian inference for improved personalization and continual learning in federated settings.

Findings

Outperforms baselines in accuracy and forgetting rate

Effective across various datasets and task distributions

Theoretically analyzed for robustness

Abstract

We focus on the problem of Personalized Federated Continual Learning (PFCL): a group of distributed clients, each with a sequence of local tasks on arbitrary data distributions, collaborate through a central server to train a personalized model at each client, with the model expected to achieve good performance on all local tasks. We propose a novel PFCL framework called Federated Memory Strengthening FedMeS to address the challenges of client drift and catastrophic forgetting. In FedMeS, each client stores samples from previous tasks using a small amount of local memory, and leverages this information to both 1) calibrate gradient updates in training process; and 2) perform KNN-based Gaussian inference to facilitate personalization. FedMeS is designed to be task-oblivious, such that the same inference process is applied to samples from all tasks to achieve good performance. FedMeS is analyzed theoretically and evaluated experimentally. It is shown to outperform all baselines in average accuracy and forgetting rate, over various combinations of datasets, task distributions, and client numbers.