← Back to all news
arXiv Machine Learning By Amin Meghrazi, Srinivasan Parthasarathy, Andrew Perrault

Pathwise Individual Rationality in Federated Learning: A Mechanism-Architecture Co-Design

Read the original on arXiv Machine Learning →

The paper investigates the trade‑off between the costs of participating in federated learning (privacy, communication, compute) and the potential gains in model performance, framing this as a game‑theoretic problem of individual rationality versus autarky. It shows that clients can remain below their local‑training baseline for many rounds and that simply capping per‑round contributions harms learning. The authors propose a new mechanism that provides short‑term participation guarantees and personalized model evaluation, demonstrating theoretically and empirically that clients can avoid short‑term losses without significantly harming overall performance, even under moderate heterogeneity.

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
Oct 15

Incentivize Contribution and Learn Parameters Too: Federated Learning with Strategic Data Owners

The paper proposes mechanisms for federated learning that both incentivize strategic data owners to contribute fully and learn a high‑quality model. The first mechanism, UPBReD, jointly updates client contributions and the model, converging to a Nash equilibrium that may involve under‑contribution. The second mechanism, 2P‑UPBReD, introduces budget‑balanced transfers to make full contribution a dominant strategy, ensuring convergence to the optimal model while guaranteeing that all clients prefer to participate. Subsequent extensions (T‑2P‑UPBReD) further enforce truthful reporting of contributions and gradients without running a deficit, and experiments on CIFAR‑10, FEMNIST, and Twitter demonstrate that 2P‑UPBReD achieves welfare comparable to FedAvg trained on all data.

By Drashthi Doshi, Avishek Ghosh, Swaprava Nath
More like this →
arXiv Machine Learning
Oct 3

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 →