Back to Search Start Over

Dynamic Heterogeneous Information Network Embedding With Meta-Path Based Proximity.

Authors :
Wang, Xiao
Lu, Yuanfu
Shi, Chuan
Wang, Ruijia
Cui, Peng
Mou, Shuai
Source :
IEEE Transactions on Knowledge & Data Engineering. Mar2022, Vol. 34 Issue 3, p1117-1132. 16p.
Publication Year :
2022

Abstract

Heterogeneous information network (HIN) embedding aims at learning the low-dimensional representation of nodes while preserving structure and semantics in a HIN. Existing methods mainly focus on static networks, while a real HIN usually evolves over time with the addition (deletion) of multiple types of nodes and edges. Because even a tiny change can influence the whole structure and semantics, the conventional HIN embedding methods need to be retrained to get the updated embeddings, which is time-consuming and unrealistic. In this paper, we investigate the problem of dynamic HIN embedding and propose a novel Dynamic HIN Embedding model (DyHNE) with meta-path based proximity. Specifically, we introduce the meta-path based first- and second-order proximities to preserve structure and semantics in HINs. As the HIN evolves over time, we naturally capture changes with the perturbation of meta-path augmented adjacency matrices. Thereafter, we learn the node embeddings by solving generalized eigenvalue problem effectively and employ eigenvalue perturbation to derive the updated embeddings efficiently without retraining. Experiments show that DyHNE outperforms the state-of-the-arts in terms of effectiveness and efficiency. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
10414347
Volume :
34
Issue :
3
Database :
Academic Search Index
Journal :
IEEE Transactions on Knowledge & Data Engineering
Publication Type :
Academic Journal
Accession number :
155108795
Full Text :
https://doi.org/10.1109/TKDE.2020.2993870