Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

8-2019

Abstract

Network embedding, which aims to represent network data in alow-dimensional space, has been commonly adopted for analyzingheterogeneous information networks (HIN). Although exiting HINembedding methods have achieved performance improvement tosome extent, they still face a few major weaknesses. Most importantly, they usually adopt negative sampling to randomly selectnodes from the network, and they do not learn the underlying distribution for more robust embedding. Inspired by generative adversarial networks (GAN), we develop a novel framework HeGAN forHIN embedding, which trains both a discriminator and a generatorin a minimax game. Compared to existing HIN embedding methods,our generator would learn the node distribution to generate betternegative samples. Compared to GANs on homogeneous networks,our discriminator and generator are designed to be relation-aware inorder to capture the rich semantics on HINs. Furthermore, towardsmore effective and efficient sampling, we propose a generalizedgenerator, which samples “latent” nodes directly from a continuousdistribution, not confined to the nodes in the original network asexisting methods are. Finally, we conduct extensive experiments onfour real-world datasets. Results show that we consistently and significantly outperform state-of-the-art baselines across all datasetsand tasks.

Keywords

Heterogeneous Information Network, Network Embedding, Generative Adversarial Network

Discipline

Databases and Information Systems | Numerical Analysis and Scientific Computing

Research Areas

Data Science and Engineering

Publication

KDD '19: Proceedings of the 25th ACM SIGKDD Conference On Knowledge Discovery and Data Mining, Anchorage, Alaska, August 4-8

First Page

120

Last Page

129

ISBN

9781450362016

Identifier

10.1145/3292500.3330970

Publisher

ACM

City or Country

New York

Copyright Owner and License

Publisher

Additional URL

https://doi.org/10.1145/3292500.3330970

Share

COinS