LGAIAug 13, 2025

Large-Small Model Collaborative Framework for Federated Continual Learning

arXiv:2508.09489v11 citationsh-index: 18
Originality Incremental advance
AI Analysis

This addresses the problem of continual learning for Foundation Models in federated settings, which is incremental as it builds on existing CL techniques.

The paper tackles the challenge of enabling Foundation Models to learn new tasks without forgetting prior knowledge in Federated Continual Learning, achieving superior performance with a collaborative framework that uses small models as a dynamic bridge.

Continual learning (CL) for Foundation Models (FMs) is an essential yet underexplored challenge, especially in Federated Continual Learning (FCL), where each client learns from a private, evolving task stream under strict data and communication constraints. Despite their powerful generalization abilities, FMs often exhibit suboptimal performance on local downstream tasks, as they are unable to utilize private local data. Furthermore, enabling FMs to learn new tasks without forgetting prior knowledge is inherently a challenging problem, primarily due to their immense parameter count and high model complexity. In contrast, small models can be trained locally under resource-constrained conditions and benefit from more mature CL techniques. To bridge the gap between small models and FMs, we propose the first collaborative framework in FCL, where lightweight local models act as a dynamic bridge, continually adapting to new tasks while enhancing the utility of the large model. Two novel components are also included: Small Model Continual Fine-tuning is for preventing small models from temporal forgetting; One-by-One Distillation performs personalized fusion of heterogeneous local knowledge on the server. Experimental results demonstrate its superior performance, even when clients utilize heterogeneous small models.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes