Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Wasserstein distance, Federated Learning ; Triangle inequality
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: We propose a federated manner of computing Wasserstein distance by exploiting its metric property and its geodesics
Abstract: We introduce a principled way of computing the Wasserstein distance between two distributions in a federated manner.
Namely, we show how to estimate the Wasserstein distance between two samples stored and
kept on different devices/clients whilst a central entity/server orchestrates the computations
(again, without having access to the samples). To achieve this feat, we take advantage of the geometric
properties of the Wasserstein distance -- in particular, the triangle inequality --
and that of the associated {\em geodesics}: our algorithm, FedWad (for Federated Wasserstein Distance), iteratively approximates
the Wasserstein distance by manipulating and exchanging distributions from the
space of geodesics in lieu of the input samples.
In addition to establishing the convergence properties of FedWad,
we provide empirical results on federated coresets and federate
optimal transport dataset distance, that we respectively exploit for
building a novel federated model and for boosting performance of popular federated learning algorithms.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
Supplementary Material: zip
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Primary Area: general machine learning (i.e., none of the above)
Submission Number: 5765
Loading