Publications · Journal article · Trans. Mach. Learn. Res. 2026
RESIST: resilient decentralized learning using consensus gradient descent
Transactions on Machine Learning Research, 2026. Featured certification.
In brief
Decentralized learning is vulnerable to man-in-the-middle attacks that alter the messages agents exchange. RESIST combines multi-step consensus gradient descent with robust-statistics screening of neighbors’ messages and converges exactly to the empirical risk minimizer — linearly for strongly convex and Polyak–Łojasiewicz problems, sublinearly for smooth non-convex ones — as long as the fraction of compromised links stays below the screening rule’s breakdown point.
Cite
@article{fang2025resist,
title = {RESIST: resilient decentralized learning using consensus gradient descent},
author = {Cheng Fang and Rishabh Dixit and Waheed U. Bajwa and Mert Gürbüzbalaban},
year = {2026},
journal = {Transactions on Machine Learning Research},
note = {arXiv:2502.07977},
}Relatedsame topics