U.S. flag

An official website of the United States government, Department of Justice.

NCJRS Virtual Library

The Virtual Library houses over 235,000 criminal justice resources, including all known OJP works.
Click here to search the NCJRS Virtual Library

Heterogeneous Information Network Embedding With Adversarial Disentangler

NCJ Number
308048
Journal
IEEE Transactions on Knowledge and Data Engineering Volume: 35 Issue: 2 Dated: 2023 Pages: 1581-1593
Author(s)
Ruijia Wang; Chuan Shi; Tianyu Zhao; Xiao Wang; Yanfang Ye
Date Published
2023
Length
13 pages
Annotation

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.

Abstract

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)