FedRAW: Preserving Rare-Label Influence in Asynchronous Federated Learning
Quick summary
arXiv:2609.07192v1 Announce Type: cross Abstract: Asynchronous federated learning improves scalability by updating the global model from a server-side buffer of client updates as they arrive, rather than waiting for all selected clients to finish. While efficient, this arrival-driven aggregation can silently distort representation learning under heterogeneous participation. We identify silent rarity failure, a hidden failure mode in which clients holding rare labels contribute too weakly to the global model even though its overall accuracy appears largely unaffected. This failure arises from t
Key takeaways
- arXiv:2609.07192v1 Announce Type: cross Abstract: Asynchronous federated learning improves scalability by updating the global model from a server-side buffer of client updates as they arrive, rather than waiting for all selected clients to finish.
- While efficient, this arrival-driven aggregation can silently distort representation learning under heterogeneous participation.
- We identify silent rarity failure, a hidden failure mode in which clients holding rare labels contribute too weakly to the global model even though its overall accuracy appears largely unaffected.
Why it matters
“FedRAW: Preserving Rare-Label Influence in Asynchronous Federated Learning” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.
Member comments