AI 中文总结
针对模型异构联邦学习中知识共享不可靠的问题，提出FedTopo框架，通过共享类关系拓扑实现可靠协作，在多数据集多骨干网络上性能优于多种基线，开销低。
AI 中文摘要
联邦学习（FL）支持在去中心化数据孤岛间开展协作学习，无需集中原始数据。但异构本地架构常引发表征空间不对齐，难以跨孤岛迁移全局知识。现有范式以模型参数、蒸馏预测或类原型形式共享知识，均编码为需在客户端间对齐的绝对空间；异构骨干网络会破坏该对齐，导致共享知识不可靠，误导本地训练。我们提出FedTopo，一种关系级框架，将全局知识编码为类关系拓扑，捕捉客户端内各类别的关联方式而非其在特征空间的位置。每个客户端基于本地原型构建自身关系拓扑，并附带类统计信息上传。服务器以感知可靠性的方式聚合这些关系，对支持度弱的关系降权，再将全局拓扑广播给客户端。全局拓扑通过强调拓扑相似的负类来指导本地训练。在三个数据集、八种异构骨干网络上的实验表明，FedTopo始终优于参数共享、蒸馏共享和原型共享基线，且通信开销低、无推理开销。我们的代码可在该https URL获取。
英文摘要
Federated learning (FL) enables collaborative learning over decentralized data silos without centralizing raw data. However, heterogeneous local architectures often induce non-aligned representation spaces, making it difficult to transfer global knowledge across silos. Existing paradigms share this knowledge as model parameters, distilled predictions, or class prototypes, yet all encode it in an absolute space that must be aligned across clients. Heterogeneous backbones break this alignment, so the shared knowledge becomes unreliable and misleads local training. We propose FedTopo, a relation-level framework that encodes global knowledge as class relation topology, capturing how classes relate within each client rather than where they lie in feature space. Each client builds its relation topology from local prototypes and uploads it with class statistics. The server then aggregates these relations in a reliability-aware manner that down-weights weakly supported ones, and broadcasts the global topology to clients. The global topology guides local training by emphasizing topology-similar negative classes. Experiments on three datasets under eight heterogeneous backbones show that FedTopo consistently outperforms parameter-, distillation-, and prototype-sharing baselines, with low communication and no inference overhead. Our code is available at https://github.com/Zhaoyang-Ma/FedTopo.
Comments13 pages, 9 figures, 4 tables. Submitted to ICDE 2027 (first submission round)
