Topological Neural Networks go Persistent, Equivariant, and Continuous

Loading...
Thumbnail Image

Access rights

openAccess
publishedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

2024

Major/Subject

Mcode

Degree programme

Language

en

Pages

20

Series

Proceedings of Machine Learning Research, Volume 235, pp. 49388-49407

Abstract

Topological Neural Networks (TNNs) incorporate higher-order relational information beyond pairwise interactions, enabling richer representations than Graph Neural Networks (GNNs). Concurrently, topological descriptors based on persistent homology (PH) are being increasingly employed to augment the GNNs. We investigate the benefits of integrating these two paradigms. Specifically, we introduce TopNets as a broad framework that subsumes and unifies various methods in the intersection of GNNs/TNNs and PH such as (generalizations of) RePHINE and TOGL. TopNets can also be readily adapted to handle (symmetries in) geometric complexes, extending the scope of TNNs and PH to spatial settings. Theoretically, we show that PH descriptors can provably enhance the expressivity of simplicial message-passing networks. Empirically, (continuous and E(n)-equivariant extensions of) TopNets achieve strong performance across diverse tasks, including antibody design, molecular dynamics simulation, and drug property prediction.

Description

Publisher Copyright: Copyright 2024 by the author(s)

Keywords

Other note

Citation

Verma, Y, Souza, A H & Garg, V 2024, ' Topological Neural Networks go Persistent, Equivariant, and Continuous ', Proceedings of Machine Learning Research, vol. 235, pp. 49388-49407 . < https://proceedings.mlr.press/v235/verma24a.html >