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. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1007/s11390-019-1971-3 | Journal of Computer Science and Technology |
Keywords | Field | DocType |
heterogeneous information network, network embedding, attention mechanism, generative adversarial network | Embedding,Autoencoder,Computer science,Semantic information,Artificial intelligence,Generative grammar,Heterogeneous network,Semantics,Distributed computing,Adversarial system,Theory of computation | Journal |
Volume | Issue | ISSN |
34 | 6 | 1000-9000 |
Citations | PageRank | References |
1 | 0.36 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chunyang Ruan | 1 | 4 | 2.42 |
Ye Wang | 2 | 7 | 2.12 |
Jiangang Ma | 3 | 148 | 17.23 |
Yanchun Zhang | 4 | 3059 | 284.90 |
Xintian Chen | 5 | 1 | 0.36 |