← Back to all news
arXiv Machine Learning By Yingzhu Liu, Zhongkui Li, Pengcheng You, Ashish Cherukuri

Distributionally Robust Federated Learning with Multi-Source Data

Read the original on arXiv Machine Learning →

The paper proposes a distributionally robust federated learning framework that handles both cross-client mixture uncertainty and within-client distributional ambiguity. It constructs a global ambiguity set as a union of local ambiguity sets, allowing client-specific ambiguity radii and a client-wise separable reformulation. The authors provide a high‑probability out‑of‑sample performance guarantee, develop a penalty‑based federated algorithm, prove its convergence under milder conditions, and validate its effectiveness through simulations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
1d ago

Latent Information Sharing for Accelerating Federated Learning

The paper introduces a latent information sharing scheme for federated learning that mitigates client drift by sharing a small amount of hidden‑layer activations. The authors demonstrate both theoretically and empirically that this approach improves training efficiency while maintaining convergence guarantees and data privacy. Compared to existing methods such as FedProx, SCAFFOLD, FedPVR, FedProto, and SplitFed, the proposed method achieves higher model accuracy within a fixed round budget without adding significant communication overhead.

By Seungjun Lee, Ensieh Khazaei, Dimitrios Hatzinakos, Baturalp Buyukates, Sunwoo Lee
safety
More like this →