Heterogeneous Network Representation Learning: A Unified Framework with Survey and Benchmark

Carl Yang, Yuxin Xiao, Yu Zhang, Yizhou Sun, Jiawei Han

Research output: Contribution to journalArticlepeer-review

Abstract

Since real-world objects and their interactions are often multi-modal and multi-typed, heterogeneous networks have been widely used as a more powerful, realistic, and generic superclass of traditional homogeneous networks (graphs). Meanwhile, representation learning (a.k.a. embedding) has recently been intensively studied and shown effective for various network mining and analytical tasks. In this work, we aim to provide a unified framework to deeply summarize and evaluate existing research on heterogeneous network embedding (HNE), which includes but goes beyond a normal survey. Since there has already been a broad body of HNE algorithms, as the first contribution of this work, we provide a generic paradigm for the systematic categorization and analysis over the merits of various existing HNE algorithms. Moreover, existing HNE algorithms, though mostly claimed generic, are often evaluated on different datasets. As the second contribution, we create four benchmark datasets with various properties regarding scale, structure, attribute/label availability, and etc. from different sources, towards handy and fair evaluations of HNE algorithms. As the third contribution, we carefully refactor and amend the implementations and create friendly interfaces for eleven popular HNE algorithms, and provide all-around comparisons among them over multiple tasks and experimental settings.

Original languageEnglish (US)
JournalIEEE Transactions on Knowledge and Data Engineering
DOIs
StateAccepted/In press - 2020

Keywords

  • Analytical models
  • benchmark
  • Benchmark testing
  • heterogeneous network
  • Heterogeneous networks
  • Mathematical model
  • representation learning
  • survey
  • Systematics
  • Task analysis
  • Toy manufacturing industry

ASJC Scopus subject areas

  • Information Systems
  • Computer Science Applications
  • Computational Theory and Mathematics

Fingerprint Dive into the research topics of 'Heterogeneous Network Representation Learning: A Unified Framework with Survey and Benchmark'. Together they form a unique fingerprint.

Cite this