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

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 (\aka~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. Understandable due to the application favor of HNE, such indirect comparisons largely hinder the proper attribution of improved task performance towards effective data preprocessing and novel technical design, especially considering the various ways possible to construct a heterogeneous network from real-world application data. Therefore, 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 13 popular HNE algorithms, and provide all-around comparisons among them over multiple tasks and experimental settings.

arXiv commentAccepted by IEEE TKDE. All code and data available at https://github.com/yangji9181/HNE

References in corpus (25)

• Distributed Representations of Words and Phrases and their Compositionality
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• Graph Embedding Techniques, Applications, and Performance: A Survey
• Fast Graph Representation Learning with PyTorch Geometric
• Complex Embeddings for Simple Link Prediction
• struc2vec: Learning Node Representations from Structural Identity
• Adversarial Attacks on Neural Networks for Graph Data
• MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences
• Representation Learning for Attributed Multiplex Heterogeneous Network
• Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations
• Learning Structural Node Embeddings Via Diffusion Wavelets
• Benchmarking Graph Neural Networks
• Strategies for Pre-training Graph Neural Networks
• InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization
• Easing Embedding Learning by Comprehensive Transcription of Heterogeneous Information Networks
• Compositional Fairness Constraints for Graph Embeddings
• Position-aware Graph Neural Networks
• Heterogeneous Deep Graph Infomax
• Knowledge Graph Embedding with Entity Neighbors and Deep Memory Network
• CubeNet: Multi-Facet Hierarchical Heterogeneous Network Construction, Analysis, and Mining

Cited by in corpus (9)

• Scalable Graph Neural Networks via Bidirectional Propagation
• xFraud: Explainable Fraud Transaction Detection
• GripNet: Graph Information Propagation on Supergraph for Heterogeneous Graphs
• CoarSAS2hvec: Heterogeneous Information Network Embedding with Balanced Network Sampling
• Knowledge Graph Embedding using Graph Convolutional Networks with Relation-Aware Attention
• Hop-Hop Relation-aware Graph Neural Networks
• Leveraging Meta-path Contexts for Classification in Heterogeneous Information Networks
• Hierarchical Metadata-Aware Document Categorization under Weak Supervision
• Network Representation Learning: From Traditional Feature Learning to Deep Learning