Bayesian Contrastive Learning on Topological Structures

Master thesis (2023)

Authors

A.J. Möllers Electrical Engineering, Mathematics and Computer Science

Contributors

E. Isufi (supervisor 1)
H.N. Kekkonen Statistics - EEMCS (supervisor 1)
Vincent Fortuin (supervisor 1)
Alexander Immer ETH Zürich (supervisor 1)
L.J.J. van Iersel Discrete Mathematics and Optimization - EEMCS (supervisor 2)
Faculty
Electrical Engineering, Mathematics and Computer Science
Copyright: © 2023 Alex Möllers
More Info
expand_more

Published Date

08-11-2023

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Abstract

In this thesis we develop a Bayesian approach to graph contrastive learning and propose a new uncertainty measure based on the disagreement in likelihood due to different positive samples. Moreover, we extend contrastive learning to simplicial complexes and show that it can be used to generate high-quality representations of edge flow data.