Dynamic Participation in Federated Learning: Benchmarks and a Knowledge Pool Plugin

TL;DR

This paper introduces a benchmarking framework for federated learning with dynamic client participation and proposes a novel Knowledge-Pool FL method to improve robustness and performance under such conditions.

Contribution

It provides the first open-source benchmark for DPFL and introduces KPFL, a plugin that enhances model stability and knowledge retention during dynamic participation.

Findings

Dynamic participation significantly degrades FL performance.

The proposed KPFL improves robustness and generalization in DPFL.

Benchmarking reveals substantial performance gaps under dynamic participation.

Abstract

Federated learning (FL) enables clients to collaboratively train a shared model in a distributed manner, setting it apart from traditional deep learning paradigms. However, most existing FL research assumes consistent client participation, overlooking the practical scenario of dynamic participation (DPFL), where clients may intermittently join or leave during training. Moreover, no existing benchmarking framework systematically supports the study of DPFL-specific challenges. In this work, we present the first open-source framework explicitly designed for benchmarking FL models under dynamic client participation. Our framework provides configurable data distributions, participation patterns, and evaluation metrics tailored to DPFL scenarios. Using this platform, we benchmark four major categories of widely adopted FL models and uncover substantial performance degradation under dynamic participation. To address these challenges, we further propose Knowledge-Pool Federated Learning (KPFL), a generic plugin that maintains a shared knowledge pool across both active and idle clients. KPFL leverages dual-age and data-bias weighting, combined with generative knowledge distillation, to mitigate instability and prevent knowledge loss. Extensive experiments demonstrate the significant impact of dynamic participation on FL performance and the effectiveness of KPFL in improving model robustness and generalization.