Byzantine Resilient and Fast Federated Few-Shot Learning

Ankit Pratap Singh, Namrata Vaswani
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45696-45706, 2024.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-singh24f, title = {{B}yzantine Resilient and Fast Federated Few-Shot Learning}, author = {Singh, Ankit Pratap and Vaswani, Namrata}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {45696--45706}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/singh24f/singh24f.pdf}, url = {https://proceedings.mlr.press/v235/singh24f.html}, 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.} }
Endnote
%0 Conference Paper %T Byzantine Resilient and Fast Federated Few-Shot Learning %A Ankit Pratap Singh %A Namrata Vaswani %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-singh24f %I PMLR %P 45696--45706 %U https://proceedings.mlr.press/v235/singh24f.html %V 235 %X 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.
APA
Singh, A.P. & Vaswani, N.. (2024). Byzantine Resilient and Fast Federated Few-Shot Learning. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:45696-45706 Available from https://proceedings.mlr.press/v235/singh24f.html.

Related Material