HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916186668662784 |
|---|---|
| author | Kim, Sunwoo Kang, Shinhwan Bu, Fanchen Lee, Soo Yong Yoo, Jaemin Shin, Kijung |
| author_facet | Kim, Sunwoo Kang, Shinhwan Bu, Fanchen Lee, Soo Yong Yoo, Jaemin Shin, Kijung |
| contents | Hypergraphs are marked by complex topology, expressing higher-order interactions among multiple nodes with hyperedges, and better capturing the topology is essential for effective representation learning. Recent advances in generative self-supervised learning (SSL) suggest that hypergraph neural networks learned from generative self supervision have the potential to effectively encode the complex hypergraph topology. Designing a generative SSL strategy for hypergraphs, however, is not straightforward. Questions remain with regard to its generative SSL task, connection to downstream tasks, and empirical properties of learned representations. In light of the promises and challenges, we propose a novel generative SSL strategy for hypergraphs. We first formulate a generative SSL task on hypergraphs, hyperedge filling, and highlight its theoretical connection to node classification. Based on the generative SSL task, we propose a hypergraph SSL method, HypeBoy. HypeBoy learns effective general-purpose hypergraph representations, outperforming 16 baseline methods across 11 benchmark datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_00638 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs Kim, Sunwoo Kang, Shinhwan Bu, Fanchen Lee, Soo Yong Yoo, Jaemin Shin, Kijung Machine Learning Hypergraphs are marked by complex topology, expressing higher-order interactions among multiple nodes with hyperedges, and better capturing the topology is essential for effective representation learning. Recent advances in generative self-supervised learning (SSL) suggest that hypergraph neural networks learned from generative self supervision have the potential to effectively encode the complex hypergraph topology. Designing a generative SSL strategy for hypergraphs, however, is not straightforward. Questions remain with regard to its generative SSL task, connection to downstream tasks, and empirical properties of learned representations. In light of the promises and challenges, we propose a novel generative SSL strategy for hypergraphs. We first formulate a generative SSL task on hypergraphs, hyperedge filling, and highlight its theoretical connection to node classification. Based on the generative SSL task, we propose a hypergraph SSL method, HypeBoy. HypeBoy learns effective general-purpose hypergraph representations, outperforming 16 baseline methods across 11 benchmark datasets. |
| title | HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2404.00638 |