解决无任务标识流式联邦持续学习中的知识混淆问题
Knowledge-Aware Evolution for Task-Free Streaming Federated Continual Learning with Arbitrary Class Overlap
- 动态切换本地与全局模型提升推理性能
- 梯度平方比平衡新旧知识，缓解遗忘
- 保留关键样本增强类别重叠下的记忆能力
联邦持续学习（FCL）通过客户端间协作，在非平稳数据下更好地平衡新知识获取与旧知识保留。然而，现有方法难以应对无任务标识、瞬时访问的流式数据，导致新旧知识混淆，且无法在本地持续推理所有遇到的类别。为此，我们提出FedKACE，包含三个组件：1）自适应机制，决定何时从本地模型切换至全局模型，以提升客户端推理性能；2）响应式梯度平衡重放策略，利用梯度平方L2范数比来平衡客户端新知识获取与旧知识保留；3）整体缓冲区维护策略，保留高信息量和边界显著样本，增强在类别重叠下的知识保留能力。多场景实验与理论分析验证了该方法的有效性。
原文摘要 · Abstract (English)
Federated Continual Learning (FCL) leverages inter-client collaboration to better balance new knowledge acquisition and old knowledge retention on non-stationary data. However, existing FCL methods struggle to adapt to streaming scenarios where sequential and ephemerally accessible data chunks lack task identifiers and exhibit arbitrary class overlap, leading to confusion between old and new knowledge and an inability to sustain local inference on all encountered classes. To address this, we propose FedKACE with three components: 1) an adaptive mechanism that determines when to switch the inference model from the local to the global one to improve client-side inference performance; 2) a responsive gradient-balanced replay scheme that utilizes the ratio of the squared L2 gradient norms to balance client-specific knowledge between new acquisition and old retention; 3) a holistic buffer maintenance strategy that preserves highly informative and boundary-significant samples to enhance knowledge retention under class overlap.Experiments across multiple scenarios and theoretical analysis demonstrate the effectiveness of FedKACE.
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。