Heterogeneous Information Network Embedding with Adversarial Disentangler
| Autor: | Yanfang Fanny Ye, Chuan Shi, Ruijia Wang, Tianyu Zhao, Xiao Wang |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Exploit
Computer science Head (linguistics) business.industry Node (networking) Machine learning computer.software_genre Semantics Computer Science Applications Adversarial system Computational Theory and Mathematics Embedding Artificial intelligence Representation (mathematics) Set (psychology) business computer Information Systems |
| Zdroj: | IEEE Transactions on Knowledge and Data Engineering. :1-1 |
| ISSN: | 2326-3865 1041-4347 |
| DOI: | 10.1109/tkde.2021.3096231 |
| Popis: | Heterogeneous information network (HIN) embedding has gained considerable attention in recent years, which learns low-dimensional representation of nodes while preserving the semantic and structural correlations in HINs. Many of existing methods which exploit meta-path guided strategy have shown promising results. However, the learned node representations could be highly entangled for downstream tasks; for example, an author's publications in multidisciplinary venues may make the prediction of his/her research interests difficult. To address this issue, we develop a novel framework named HEAD (i.e., HIN Embedding with Adversarial Disentangler) to separate the distinct, informative factors of variations in node semantics formulated by meta-paths. More specifically, in HEAD, we first propose the meta-path disentangler to separate node embeddings from various meta-paths into intrinsic and specific spaces; then with meta-path schemes as self-supervised information, we design two adversarial learners (i.e., meta-path and semantic discriminators) to make the intrinsic embedding more independent from the designed meta-paths while the specific embedding more meta-path dependent. To comprehensively evaluate the performance of HEAD, we perform a set of experiments on four real-world datasets. Compared to the state-of-the-art baselines, the maximum 15% improvement of performance demonstrates the effectiveness of HEAD and the benefits of the learned disentangled representations. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|