RSA: Byzantine-robust stochastic aggregation methods for distributed learning from heterogeneous datasets

Liping Li, Wei Xu, Tianyi Chen, Georgios B. Giannakis, Qing Ling

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Scopus citations

Abstract

In this paper, we propose a class of robust stochastic subgradient methods for distributed learning from heterogeneous datasets at presence of an unknown number of Byzantine workers. The Byzantine workers, during the learning process, may send arbitrary incorrect messages to the master due to data corruptions, communication failures or malicious attacks, and consequently bias the learned model. The key to the proposed methods is a regularization term incorporated with the objective function so as to robustify the learning task and mitigate the negative effects of Byzantine attacks. The resultant subgradient-based algorithms are termed Byzantine-Robust Stochastic Aggregation methods, justifying our acronym RSA used henceforth. In contrast to most of the existing algorithms, RSA does not rely on the assumption that the data are independent and identically distributed (i.i.d.) on the workers, and hence fits for a wider class of applications. Theoretically, we show that: i) RSA converges to a near-optimal solution with the learning error dependent on the number of Byzantine workers; ii) the convergence rate of RSA under Byzantine attacks is the same as that of the stochastic gradient descent method, which is free of Byzantine attacks. Numerically, experiments on real dataset corroborate the competitive performance of RSA and a complexity reduction compared to the state-of-the-art alternatives.

Original languageEnglish (US)
Title of host publication33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019
PublisherAAAI press
Pages1544-1551
Number of pages8
ISBN (Electronic)9781577358091
StatePublished - 2019
Event33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Annual Conference on Innovative Applications of Artificial Intelligence, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019 - Honolulu, United States
Duration: Jan 27 2019Feb 1 2019

Publication series

Name33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019

Conference

Conference33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Annual Conference on Innovative Applications of Artificial Intelligence, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019
Country/TerritoryUnited States
CityHonolulu
Period1/27/192/1/19

Bibliographical note

Funding Information:
Acknowledgments. The work by T. Chen and G. Gian-nakis is supported in part by NSF 1500713 and 1711471. The work by Q. Ling is supported in part by NSF China 61573331 and Guangdong IIET 2017ZT07X355.

Publisher Copyright:
© 2019, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

Fingerprint

Dive into the research topics of 'RSA: Byzantine-robust stochastic aggregation methods for distributed learning from heterogeneous datasets'. Together they form a unique fingerprint.

Cite this