Higher-Order Topological Directionality and Directed Simplicial Neural Networks

Conference Paper (2025)
Author(s)

Manuel Lecha (Istituto Italiano di Tecnologia)

A. Cavallo (TU Delft - Multimedia Computing)

Francesca Dominici (Harvard University)

E. Isufi (TU Delft - Multimedia Computing)

Claudio Battiloro (Harvard University)

Research Group
Multimedia Computing
DOI related publication
https://doi.org/10.1109/ICASSP49660.2025.10890264
More Info
expand_more
Publication Year
2025
Language
English
Research Group
Multimedia Computing
Publisher
IEEE
ISBN (electronic)
979-8-3503-6874-1
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.

Abstract

Topological Deep Learning (TDL) has emerged as a paradigm to process and learn from signals defined on higher-order combinatorial topological spaces, such as simplicial or cell complexes. Although many complex systems have an asymmetric relational structure, most TDL models forcibly symmetrize these relationships. In this paper, we first introduce a novel notion of higher-order directionality and we then design Directed Simplicial Neural Networks (Dir-SNNs) based on it. Dir-SNNs are message-passing networks operating on directed simplicial complexes able to leverage directed and possibly asymmetric interactions among the simplices. To our knowledge, this is the first TDL model using a notion of higher-order directionality. We theoretically and empirically prove that Dir-SNNs are more expressive than their directed graph counterpart in distinguishing non-isomorphic directed graphs. Experiments on a synthetic source localization task demonstrate that Dir-SNNs outperform undirected SNNs when the underlying complex is directed, and perform comparably when the underlying complex is undirected.

Files

Higher-Order_Topological_Direc... (pdf)
(pdf | 1.08 Mb)
- Embargo expired in 27-01-2026
Taverne