Heterogeneous Hypernetwork Representation Learning Based on Importance Sampling
Saved in:
| Title: | Heterogeneous Hypernetwork Representation Learning Based on Importance Sampling |
|---|---|
| Authors: | XIA Qingqing, ZHU Yu, WANG Xiaoying, HUANG Jianqiang, CAO Tengfei |
| Source: | Jisuanji gongcheng, Vol 51, Iss 11, Pp 133-143 (2025) |
| Publisher Information: | Editorial Office of Computer Engineering, 2025. |
| Publication Year: | 2025 |
| Collection: | LCC:Computer engineering. Computer hardware LCC:Computer software |
| Subject Terms: | representation learning, high-order tuple relation, importance sampling, data augmentation, negative sampling enhancement, link prediction, hypernetwork reconstruction, Computer engineering. Computer hardware, TK7885-7895, Computer software, QA76.75-76.765 |
| Description: | Heterogeneous hypernetworks can model various high-order tuple relations found in the real world, which represent heterogeneous high-order information within the hypernetwork. However, heterogeneous hypernetworks have different degrees of indecomposability, and existing research methods do not fully consider the indecomposability of high-order tuple relations regarded as hyperedges. To address this issue, a heterogeneous hypernetwork representation learning method based on importance sampling, called HRIS, is proposed, which incorporates close high-order tuple relations into hypernetwork representation learning. First, it proposes judgment nodes, and incorporates indecomposable factors and tuple similarity to improve the sampling of important nodes through random walks to capture tight high-order tuple relations within the hypernetwork. Second, to make the sequences more global and diverse, the random swap method in data augmentation is introduced for solving overfitting problems, and a random deletion method based on node degree is proposed to improve robustness. Finally, a skip-gram model with negative sampling enhancement, called NSE-skip-gram, is proposed to obtain high-quality node representation vectors. Experiments conducted on four real hypernetwork datasets reveal that for the link prediction task, the HRIS demonstrates a significant improvement over other baseline methods; for the hypernetwork reconstruction task, the HRIS exhibits an average improvement of 3.75 and 9.79 percentage points compared to the optimal baseline method on the Global Positioning System (GPS) and drug datasets at all reconstruction ratios, respectively. |
| Document Type: | article |
| File Description: | electronic resource |
| Language: | English Chinese |
| ISSN: | 1000-3428 |
| Relation: | https://www.ecice06.com/fileup/1000-3428/PDF/jsjgc-51-11-133.pdf; https://doaj.org/toc/1000-3428 |
| DOI: | 10.19678/j.issn.1000-3428.0069679 |
| Access URL: | https://doaj.org/article/95c9402776ab4c46828d1dadf19ab7f9 |
| Accession Number: | edsdoj.95c9402776ab4c46828d1dadf19ab7f9 |
| Database: | Directory of Open Access Journals |
Nájsť tento článok vo Web of Science | Abstract: | Heterogeneous hypernetworks can model various high-order tuple relations found in the real world, which represent heterogeneous high-order information within the hypernetwork. However, heterogeneous hypernetworks have different degrees of indecomposability, and existing research methods do not fully consider the indecomposability of high-order tuple relations regarded as hyperedges. To address this issue, a heterogeneous hypernetwork representation learning method based on importance sampling, called HRIS, is proposed, which incorporates close high-order tuple relations into hypernetwork representation learning. First, it proposes judgment nodes, and incorporates indecomposable factors and tuple similarity to improve the sampling of important nodes through random walks to capture tight high-order tuple relations within the hypernetwork. Second, to make the sequences more global and diverse, the random swap method in data augmentation is introduced for solving overfitting problems, and a random deletion method based on node degree is proposed to improve robustness. Finally, a skip-gram model with negative sampling enhancement, called NSE-skip-gram, is proposed to obtain high-quality node representation vectors. Experiments conducted on four real hypernetwork datasets reveal that for the link prediction task, the HRIS demonstrates a significant improvement over other baseline methods; for the hypernetwork reconstruction task, the HRIS exhibits an average improvement of 3.75 and 9.79 percentage points compared to the optimal baseline method on the Global Positioning System (GPS) and drug datasets at all reconstruction ratios, respectively. |
|---|---|
| ISSN: | 10003428 |
| DOI: | 10.19678/j.issn.1000-3428.0069679 |