Data-Free Federated Class Incremental Learning with Diffusion-Based Generative Memory

no code implementations • 22 May 2024 • Naibo Wang, Yuchen Deng, Wenjie Feng, Jianwei Yin, See-Kiong Ng

In this paper, we introduce a novel data-free federated class incremental learning framework with diffusion-based generative memory (DFedDGM) to mitigate catastrophic forgetting by generating stable, high-quality images through diffusion models.

Class Incremental Learning Federated Learning +3

One-Shot Sequential Federated Learning for Non-IID Data by Enhancing Local Model Diversity

no code implementations • 18 Apr 2024 • Naibo Wang, Yuchen Deng, Wenjie Feng, Shichen Fan, Jianwei Yin, See-Kiong Ng

In this paper, we improve the one-shot sequential federated learning for non-IID data by proposing a local model diversity-enhancing strategy.

Federated Learning