Disentangling Hyperedges through the Lens of Category Theory
This work addresses hyperedge disentanglement for hypergraph neural networks, which is an incremental advancement in representation learning for structured data.
The paper tackled the problem of disentangling hyperedges in hypergraph-structured data by proposing a novel criterion derived from category theory, and the proof-of-concept model successfully captured functional gene relations in genetic pathways.
Despite the promising results of disentangled representation learning in discovering latent patterns in graph-structured data, few studies have explored disentanglement for hypergraph-structured data. Integrating hyperedge disentanglement into hypergraph neural networks enables models to leverage hidden hyperedge semantics, such as unannotated relations between nodes, that are associated with labels. This paper presents an analysis of hyperedge disentanglement from a category-theoretical perspective and proposes a novel criterion for disentanglement derived from the naturality condition. Our proof-of-concept model experimentally showed the potential of the proposed criterion by successfully capturing functional relations of genes (nodes) in genetic pathways (hyperedges).