FedTopo: Relation-Level Topology Sharing for Model-Heterogeneous Federated Learning
Quick summary
arXiv:2607.26801v1 Announce Type: cross Abstract: 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 mislea
Key takeaways
- arXiv:2607.26801v1 Announce Type: cross Abstract: 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.
Why it matters
This model development creates a new option for users and a new testing obligation for developers. A fixed evaluation set comparing quality, cost and failure behavior is more useful than launch claims.