Version 1
: Received: 13 January 2018 / Approved: 17 January 2018 / Online: 17 January 2018 (05:20:53 CET)
How to cite:
Fang, Y.; Zhao, X.; Tan, Z. TransPath: Representation Learning for Heterogeneous Information Networks via Translation Mechanism. Preprints2018, 2018010147. https://doi.org/10.20944/preprints201801.0147.v1.
Fang, Y.; Zhao, X.; Tan, Z. TransPath: Representation Learning for Heterogeneous Information Networks via Translation Mechanism. Preprints 2018, 2018010147. https://doi.org/10.20944/preprints201801.0147.v1.
Cite as:
Fang, Y.; Zhao, X.; Tan, Z. TransPath: Representation Learning for Heterogeneous Information Networks via Translation Mechanism. Preprints2018, 2018010147. https://doi.org/10.20944/preprints201801.0147.v1.
Fang, Y.; Zhao, X.; Tan, Z. TransPath: Representation Learning for Heterogeneous Information Networks via Translation Mechanism. Preprints 2018, 2018010147. https://doi.org/10.20944/preprints201801.0147.v1.
Abstract
In this paper, we propose a novel network representation learning model TransPath to encode heterogeneous information networks (HINs). Traditional network representation learning models aim to learn the embeddings of a homogeneous network. TransPath is able to capture the rich semantic and structure information of a HIN via meta-paths. We take advantage of the concept of translation mechanism in knowledge graph which regards a meta-path, instead of an edge, as a translating operation from the first node to the last node. Moreover, we propose a user-guided meta-path sampling strategy which takes users' preference as a guidance, which could explore the semantics of a path more precisely, and meanwhile improve model efficiency via the avoidance of other noisy and meaningless meta-paths. We evaluate our model on two large-scale real-world datasets DBLP and YELP, and two benchmark tasks similarity search and node classification. We observe that TransPath outperforms other state-of-the-art baselines consistently and significantly.
Keywords
heterogeneous information network; representation learning
Subject
MATHEMATICS & COMPUTER SCIENCE, Information Technology & Data Management
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.