解决联邦持续学习中跨客户端类别知识不一致问题，提升模型长期性能。
C^2Prompt: Class-aware Client Knowledge Interaction for Federated Continual Learning
- 通过类感知机制增强客户端间提示的类别一致性
- 在多个基准上达到当前最佳性能，显著减少遗忘
- 适合研究联邦学习与持续学习交叉方向的学者
联邦持续学习（FCL）处理分布式客户端随时间不断涌现的任务数据，核心挑战在于同时应对时间遗忘和空间遗忘。现有基于提示的FCL方法虽表现优异，但存在客户端间提示的类别知识连贯性不足的问题，包括类内分布差异导致语义不一致，以及类间提示相关性引发跨类别混淆。这加剧了新旧提示间的知识冲突，恶化遗忘现象。为此，本文提出类感知客户端知识交互（C²Prompt）方法，引入局部类分布补偿机制（LCDC）以缩小客户端间类内分布差异，强化类内知识一致性；设计类感知提示聚合方案（CPA），选择性加强类相关知识聚合，缓解类间混淆。在多个FCL基准上的实验表明，该方法性能领先。源码已公开。
原文摘要 · Abstract (English)
Federated continual learning (FCL) tackles scenarios of learning from continuously emerging task data across distributed clients, where the key challenge lies in addressing both temporal forgetting over time and spatial forgetting simultaneously. Recently, prompt-based FCL methods have shown advanced performance through task-wise prompt communication.In this study, we underscore that the existing prompt-based FCL methods are prone to class-wise knowledge coherence between prompts across clients. The class-wise knowledge coherence includes two aspects: (1) intra-class distribution gap across clients, which degrades the learned semantics across prompts, (2) inter-prompt class-wise relevance, which highlights cross-class knowledge confusion. During prompt communication, insufficient class-wise coherence exacerbates knowledge conflicts among new prompts and induces interference with old prompts, intensifying both spatial and temporal forgetting. To address these issues, we propose a novel Class-aware Client Knowledge Interaction (C${}^2$Prompt) method that explicitly enhances class-wise knowledge coherence during prompt communication. Specifically, a local class distribution compensation mechanism (LCDC) is introduced to reduce intra-class distribution disparities across clients, thereby reinforcing intra-class knowledge consistency. Additionally, a class-aware prompt aggregation scheme (CPA) is designed to alleviate inter-class knowledge confusion by selectively strengthening class-relevant knowledge aggregation. Extensive experiments on multiple FCL benchmarks demonstrate that C${}^2$Prompt achieves state-of-the-art performance. Our source code is available at https://github.com/zhoujiahuan1991/NeurIPS2025-C2Prompt
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。