HyGEN: Regularizing Negative Hyperedge Generation for Accurate Hyperedge Prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915156811841536 |
|---|---|
| author | Yu, Song Kyung Lee, Da Eun Ko, Yunyong Kim, Sang-Wook |
| author_facet | Yu, Song Kyung Lee, Da Eun Ko, Yunyong Kim, Sang-Wook |
| contents | Hyperedge prediction is a fundamental task to predict future high-order relations based on the observed network structure. Existing hyperedge prediction methods, however, suffer from the data sparsity problem. To alleviate this problem, negative sampling methods can be used, which leverage non-existing hyperedges as contrastive information for model training. However, the following important challenges have been rarely studied: (C1) lack of guidance for generating negatives and (C2) possibility of producing false negatives. To address them, we propose a novel hyperedge prediction method, HyGEN, that employs (1) a negative hyperedge generator that employs positive hyperedges as a guidance to generate more realistic ones and (2) a regularization term that prevents the generated hyperedges from being false negatives. Extensive experiments on six real-world hypergraphs reveal that HyGEN consistently outperforms four state-of-the-art hyperedge prediction methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_05827 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HyGEN: Regularizing Negative Hyperedge Generation for Accurate Hyperedge Prediction Yu, Song Kyung Lee, Da Eun Ko, Yunyong Kim, Sang-Wook Social and Information Networks Artificial Intelligence Hyperedge prediction is a fundamental task to predict future high-order relations based on the observed network structure. Existing hyperedge prediction methods, however, suffer from the data sparsity problem. To alleviate this problem, negative sampling methods can be used, which leverage non-existing hyperedges as contrastive information for model training. However, the following important challenges have been rarely studied: (C1) lack of guidance for generating negatives and (C2) possibility of producing false negatives. To address them, we propose a novel hyperedge prediction method, HyGEN, that employs (1) a negative hyperedge generator that employs positive hyperedges as a guidance to generate more realistic ones and (2) a regularization term that prevents the generated hyperedges from being false negatives. Extensive experiments on six real-world hypergraphs reveal that HyGEN consistently outperforms four state-of-the-art hyperedge prediction methods. |
| title | HyGEN: Regularizing Negative Hyperedge Generation for Accurate Hyperedge Prediction |
| topic | Social and Information Networks Artificial Intelligence |
| url | https://arxiv.org/abs/2502.05827 |