发表机构
AIDAS Lab; IPAI; ECE, Seoul National University（AIDAS实验室; IPAI; 首尔国立大学电子与计算机工程系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对联邦类增量学习中时空干扰致灾难性遗忘问题，本文提出SUM框架，将其视为统一多任务学习，在聚合时对适应向量做几何手术，减轻客户端干扰与跨任务干扰，实验显示该方法在多基准测试中效果显著提升。
AI 中文摘要
现实世界的智能系统需要跨数据隔离客户端的分布式协作以及对不断演变任务的持续适应，这催生了联邦类增量学习（FCIL），它结合了联邦学习（FL）和持续学习（CL）。但二者结合引入了空间和时间干扰，导致时空灾难性遗忘（ST-CF）。现有方法通常分别处理干扰，会带来额外计算或通信。本文将FCIL重新解释为统一多任务学习问题，提出SUM框架，在聚合时对适应向量进行几何手术。空间SUM减轻客户端干扰，因果在线时间SUM消除跨任务干扰。实验表明，SUM在不同基准上比现有方法提升达22%，对不可靠客户端稳健且保持计算效率。
英文摘要
Real-world intelligent systems often require both distributed collaboration across data-isolated clients and continual adaptation to evolving tasks. This setting naturally gives rise to Federated Class Incremental Learning (FCIL), which combines Federated Learning (FL) and Continual Learning (CL). However, their combination introduces two coupled sources of interference: spatial interference from heterogeneous clients and temporal interference from sequential tasks, jointly leading to Spatial-Temporal Catastrophic Forgetting (ST-CF). Existing approaches typically address spatial and temporal interference with separate mechanisms, often incurring additional client-side computation or communication, while leaving directional interactions among updates during aggregation unregulated. In this paper, we reinterpret FCIL as a unified multi-task learning problem, where both client and task updates are represented as adaptation vectors in a shared parameter space. Based on this view, we propose Unified Geometric Surgery on Spatio-Temporal Adaptation Vectors (SUM), a purely server-side framework that performs geometric surgery on adaptation vectors during aggregation. Spatial SUM mitigates client-level interference within each round, while causal online temporal SUM removes cross-task interference over time without additional client-side computation, communication, or memory beyond standard federated training. Empirically, SUM achieves up to 22% improvement over prior FCIL methods across diverse vision and language benchmarks while remaining robust to unreliable clients and maintaining computational efficiency.
CommentsAccepted to ECCV 2026
