In this study, the authors 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.
The authors 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. Heterogeneous information network (HIN) embedding, which learns low-dimensional representation of nodes while preserving the semantic and structural correlations in HINs, has gained considerable attention in recent years. Many of the 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. More specifically, in HEAD, the authors 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, the authors 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, the authors perform a set of experiments on four real-world datasets. (Published Abstract Provided)