无重放梯度投影的任务无关联邦持续学习
Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection
AI总结：
提出FedProTIP框架，通过随机奇异值分解提取客户端共享任务子空间，并利用梯度投影减少任务间干扰，实现无重放、任务无关的联邦持续学习。
摘要：
联邦持续学习（FCL）使得分布式客户端能够在顺序到达的任务上协作训练模型，而无需重新访问过去的数据。然而，现有方法常常遭受灾难性遗忘，依赖可能违反隐私约束的重放缓冲区或生成模型，或者假设推理过程中已知任务身份。我们提出FedProTIP（基于投影的联邦持续学习与任务身份预测），这是一个无重放的FCL框架，它在客户端之间维护共享的任务特定特征子空间。每个客户端使用随机奇异值分解从中间激活中提取低秩核心基，捕获与当前任务相关的主要特征方向。这些基被传输到服务器并聚合以构建全局任务子空间，这些子空间捕获跨客户端的共享特征方向，而无需数据共享。在训练期间，客户端更新被投影到先前学习子空间的正交补上，以减少跨任务干扰并缓解灾难性遗忘。学习到的子空间在推理期间也被重用，通过子空间相关性估计任务身份，从而实现无需显式任务标签的任务无关预测。在CIFAR100、ImageNet-R和DomainNet上的实验表明，FedProTIP在保持更低的训练时间、内存占用和通信成本的同时，始终优于最先进的联邦持续学习基线。
英文摘要：
Federated continual learning (FCL) enables collaborative model training across distributed clients on sequentially arriving tasks without revisiting past data. However, existing approaches often suffer from catastrophic forgetting, rely on replay buffers or generative models that may violate privacy constraints, or assume knowledge of task identities during inference. We propose FedProTIP (Federated Projection-based Continual Learning with Task Identity Prediction), a replay-free FCL framework that maintains shared task-specific feature subspaces across clients. Each client extracts low-rank core bases from intermediate activations using randomized singular value decomposition, capturing dominant feature directions associated with the current task. These bases are transmitted to the server and aggregated to construct global task subspaces that capture shared feature directions across clients without requiring data sharing. During training, client updates are projected onto the orthogonal complement of previously learned subspaces to reduce cross-task interference and mitigate catastrophic forgetting. The learned subspaces are also reused during inference to estimate task identity via subspace relevance, enabling task-agnostic prediction without requiring explicit task labels. Experiments on CIFAR100, ImageNet-R, and DomainNet demonstrate that FedProTIP consistently outperforms state-of-the-art federated continual learning baselines while maintaining lower training time, memory footprint, and communication cost.
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。
