Bayesian Contrastive Learning on Topological Structures

Möllers, A.J.

Bayesian Contrastive Learning on Topological Structures

Master thesis (2023)

Authors

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

Contributors

E. Isufi (mentor)

H.N. Kekkonen Statistics - (mentor)

Vincent Fortuin (mentor)

Alexander Immer ETH Zürich (mentor)

L.J.J. van Iersel Discrete Mathematics and Optimization - (graduation committee member)

Faculty

Electrical Engineering, Mathematics and Computer Science, Electrical Engineering, Mathematics and Computer Science

Contrastive Learning Bayesian Contrastive Learning Simplicial Complexes

To reference this document use:

http://resolver.tudelft.nl/uuid:0a7fdcf0-2521-4a89-9687-8d1311d5e93d

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.

Files

Master_thesis_amoellers_tudelf... (pdf)

(pdf | 6.77 Mb)

Unknown license