- Title
- Adversarial heterogeneous network embedding with metapath attention mechanism
- Creator
- Ruan, Chunyang; Wang, Ye; Ma, Jiangang; Zhang, Yanchun; Chen, Xintian
- Date
- 2019
- Type
- Text; Journal article
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/171187
- Identifier
- vital:14262
- Identifier
-
https://doi.org/10.1007/s11390-019-1971-3
- Identifier
- ISBN:1000-9000
- Abstract
- Heterogeneous information network (HIN)-structured data provide an effective model for practical purposes in real world. Network embedding is fundamental for supporting the network-based analysis and prediction tasks. Methods of network embedding that are currently popular normally fail to effectively preserve the semantics of HIN. In this study, we propose AGA2Vec, a generative adversarial model for HIN embedding that uses attention mechanisms and meta-paths. To capture the semantic information from multi-typed entities and relations in HIN, we develop a weighted meta-path strategy to preserve the proximity of HIN. We then use an autoencoder and a generative adversarial model to obtain robust representations of HIN. The results of experiments on several real-world datasets show that the proposed approach outperforms state-of-the-art approaches for HIN embedding. © 2019, Springer Science+Business Media, LLC & Science Press, China.
- Publisher
- Springer
- Relation
- Journal of Computer Science and Technology Vol. 34, no. 6 (2019), p. 1217-1229
- Rights
- ©2019 Springer Science + Business Media, LLC & Science Press
- Rights
- This metadata is freely available under a CCO license
- Subject
- 08 Information and Computing Sciences; Attention mechanism; Generative adversarial network; Heterogeneous information network; Network embedding
- Reviewed
- Hits: 3112
- Visitors: 2942
- Downloads: 0
Thumbnail | File | Description | Size | Format |
---|