具有类别重叠和无任务标识符的流式联邦持续学习中的知识感知进化
Knowledge-Aware Evolution for Task-Free Streaming Federated Continual Learning with Arbitrary Class Overlap
AI总结：
FedKACE通过自适应推理模型切换、梯度平衡重放和核谱边界缓冲区维护，解决流式联邦持续学习中类别重叠和无任务标识符带来的知识混淆问题。
摘要：
联邦持续学习（FCL）利用客户端之间的协作，在非平稳数据中平衡新知识的获取和先前知识的保留。然而，现有的批量基于FCL方法缺乏对流式场景的适应性，这些场景中旧数据和新数据之间存在类别重叠，并且没有任务标识符，导致旧知识和新知识难以区分，样本的任务分配不确定，知识混淆。为了解决这个问题，我们提出了流式联邦持续学习的设置：在每次联邦学习（FL）轮次中，客户端处理流式数据，这些数据具有不相交的样本和可能重叠的类别，且没有任务标识符，需要在每次FL轮次后持续保持对所有先前类别的推理能力。接下来，我们引入了FedKACE：1）一个自适应推理模型切换机制，使模型能够单向切换从本地模型到全局模型，以在个性化和泛化之间取得平衡；2）一个自适应梯度平衡重放方案，在类别重叠场景下协调新知识的学习和旧知识的保留；3）一个核谱边界缓冲区维护机制，保留高信息量和高边界影响的样本以优化跨轮次的知识保留。在多个场景中的实验和后悔分析证明了FedKACE的有效性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
