Byzantine Resilient and Fast Federated Few-Shot Learning

Ankit Pratap Singh; Namrata Vaswani

ICML 2024poster4 citations

Byzantine Resilient and Fast Federated Few-Shot Learning

Abstract

This work introduces a Byzantine resilient solution for learning low-dimensional linear representation. Our main contribution is the development of a provably Byzantine-resilient AltGDmin algorithm for solving this problem in a federated setting. We argue that our solution is sample-efficient, fast, and communicationefficient. In solving this problem, we also introduce a novel secure solution to the federated subspace learning meta-problem that occurs in many different applications.

BibTeX

@inproceedings{
singh2024byzantine,
title={Byzantine Resilient and Fast Federated Few-Shot Learning},
author={Ankit Pratap Singh and Namrata Vaswani},
booktitle={Forty-first International Conference on Machine Learning},
year={2024},
url={https://openreview.net/forum?id=q5q59s2WJy}
}