Due to their ability to model meaningful higher order relations among a set of entities, higher order network models have emerged recently as a powerful alternative for graph-based …
H Tian, R Zafarani - arXiv preprint arXiv:2402.19414, 2024 - arxiv.org
Network data has become widespread, larger, and more complex over the years. Traditional network data is dyadic, capturing the relations among pairs of entities. With the need to …
The pairwise interaction paradigm of graph machine learning has predominantly governed the modelling of relational systems. However, graphs alone cannot capture the multi-level …
Networks—or graphs—are universal descriptors of systems of interacting elements. In biomedicine and healthcare, they can represent, for example, molecular interactions …
CWJ Goh, C Bodnar, P Lio - arXiv preprint arXiv:2204.09455, 2022 - arxiv.org
Graph representation learning methods have mostly been limited to the modelling of node- wise interactions. Recently, there has been an increased interest in understanding how …
We present simplicial neural networks (SNNs), a generalization of graph neural networks to data that live on a class of topological spaces called simplicial complexes. These are natural …
H Madhu, SP Chepuri - Advances in Neural Information …, 2024 - proceedings.neurips.cc
In this paper, we introduce $\texttt {TopoSRL} $, a novel self-supervised learning (SSL) method for simplicial complexes to effectively capture higher-order interactions and preserve …
R Zhang, Y Zou, J Ma - arXiv preprint arXiv:1911.02613, 2019 - arxiv.org
Graph representation learning for hypergraphs can be used to extract patterns among higher-order interactions that are critically important in many real world problems. Current …
Graph-structured data, where nodes exhibit either pair-wise or high-order relations, are ubiquitous and essential in graph learning. Despite the great achievement made by existing …