← Back to all news
arXiv Machine Learning By Honoka Anada, Tatsuya Kaneko, Yafei Ou, Shinya Takamaeda-Yamazaki

TRIP-Shapley: Propagation-Aware Contribution Attribution Framework for Peer-to-Peer Federated Learning

Read the original on arXiv Machine Learning →

TRIP-Shapley is a propagation‑aware contribution attribution framework for peer‑to‑peer federated learning that avoids explicit multi‑round path tracking by computing round‑wise contribution scores and propagating only scalar values. This approach reduces communication costs by up to 45.8× compared to the DICE method while still attributing influence across the entire training process. The framework also includes lightweight defenses against misreporting attacks, which effectively lower contribution inflation in evaluated scenarios.

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 2

Compression Footprints as Security Signals for Model-Poisoning Defense in Federated Learning

The paper proposes using lossy compression as a security signal in federated learning by defining a "compression footprint"—a low‑dimensional set of statistics derived from the compressor’s output. It introduces CRAFT, a server‑side aggregation method that leverages these footprints to distinguish honest from malicious updates without extra client metadata or knowledge of attacker numbers. Experiments on six attacks and datasets show CRAFT often outperforms existing robust aggregation baselines, demonstrating that compression can simultaneously reduce communication and enhance security.

By Sachi Shome, William Eiers
efficiency
More like this →
arXiv Machine Learning
Sep 15

End-to-End Verifiable and Robust Federated Learning

arXiv:2609.15521v1 Announce Type: new Abstract: Federated learning enables multiple parties to train a shared model without centralizing raw data with the help of an aggregator, but introduces integr...

By Doryan Lesaignoux, Enrique M\'armol Campos, Gabriele Spini, Jos\'e L. Hern\'andez-Ramos, Stephan Krenn
More like this →