MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding

Abstract

A large number of real-world graphs or networks are inherently heterogeneous, involving a diversity of node types and relation types. Heterogeneous graph embedding is to embed rich structural and semantic information of a heterogeneous graph into low-dimensional node representations. Existing models usually define multiple metapaths in a heterogeneous graph to capture the composite relations and guide neighbor selection. However, these models either omit node content features, discard intermediate nodes along the metapath, or only consider one metapath. To address these three limitations, we propose a new model named Metapath Aggregated Graph Neural Network (MAGNN) to boost the final performance. Specifically, MAGNN employs three major components, i.e., the node content transformation to encapsulate input node attributes, the intra-metapath aggregation to incorporate intermediate semantic nodes, and the inter-metapath aggregation to combine messages from multiple metapaths. Extensive experiments on three real-world heterogeneous graph datasets for node classification, node clustering, and link prediction show that MAGNN achieves more accurate prediction results than state-of-the-art baselines.

To appear at WWW 2020; 11 pages, 4 figures; typos of model name corrected

References in corpus (13)

• Efficient Estimation of Word Representations in Vector Space
• DeepWalk: Online Learning of Social Representations
• LINE: Large-scale Information Network Embedding
• Inductive Representation Learning on Large Graphs
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
• Graph Convolutional Matrix Completion
• Knowledge Graph Convolutional Networks for Recommender Systems
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• Interaction Networks for Learning about Objects, Relations and Physics
• Representation Learning for Attributed Multiplex Heterogeneous Network
• Meta-Path Guided Embedding for Similarity Search in Large-Scale Heterogeneous Information Networks
• Position-aware Graph Neural Networks

Cited by in corpus (74)

• A Comprehensive Survey on Graph Anomaly Detection with Deep Learning
• A Comprehensive Survey on Community Detection with Deep Learning
• Heterogeneous Graph Contrastive Learning for Recommendation
• Interpretable and Efficient Heterogeneous Graph Convolutional Network
• Multiplex Heterogeneous Graph Convolutional Network
• Heterogeneous Graph Representation Learning with Relation Awareness
• The Evolution of Distributed Systems for Graph Neural Networks and their Origin in Graph Processing and Deep Learning: A Survey
• DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks
• Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks
• Beyond Low-pass Filtering: Graph Convolutional Networks with Automatic Filtering
• Bringing order into the realm of Transformer-based language models for artificial intelligence and law
• xFraud: Explainable Fraud Transaction Detection
• Self-Supervised Hyperboloid Representations from Logical Queries over Knowledge Graphs
• HMSG: Heterogeneous Graph Neural Network based on Metapath Subgraph Learning
• Drug-Target Interaction/Affinity Prediction: Deep Learning Models and Advances Review
• Homophily-oriented Heterogeneous Graph Rewiring
• Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network
• Few-shot link prediction via graph neural networks for Covid-19 drug-repurposing
• Medical Entity Disambiguation Using Graph Neural Networks
• Heterogeneous Graph Contrastive Learning with Meta-path Contexts and Adaptively Weighted Negative Samples
• AutoGraph: Automated Graph Neural Network
• Efficient Heterogeneous Graph Learning via Random Projection
• Heterogeneous Network Representation Learning: A Unified Framework with Survey and Benchmark
• Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning
• Graph-adaptive Rectified Linear Unit for Graph Neural Networks
• Enabling Homogeneous GNNs to Handle Heterogeneous Graphs via Relation Embedding
• Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks
• A Network Science perspective of Graph Convolutional Networks: A survey
• Automatic Meta-Path Discovery for Effective Graph-Based Recommendation
• Inductive Meta-path Learning for Schema-complex Heterogeneous Information Networks
• Convolutional Learning on Multigraphs
• Incorporating Attributes and Multi-Scale Structures for Heterogeneous Graph Contrastive Learning
• GSim: A Graph Neural Network based Relevance Measure for Heterogeneous Graphs
• Higher-Order Attribute-Enhancing Heterogeneous Graph Neural Networks
• Large Language Model-driven Meta-structure Discovery in Heterogeneous Information Network
• Optimal Solving of Constrained Path-Planning Problems with Graph Convolutional Networks and Optimized Tree Search
• Advancing Biomedicine with Graph Representation Learning: Recent Progress, Challenges, and Future Directions
• Cross-Network Learning with Partially Aligned Graph Convolutional Networks
• GRAF: Graph Attention-aware Fusion Networks
• Graph-Skeleton: ~1% Nodes are Sufficient to Represent Billion-Scale Graph
• Heterogeneous Social Event Detection via Hyperbolic Graph Representations
• LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations
• Hybrid Micro/Macro Level Convolution for Heterogeneous Graph Learning
• Balanced Multi-Relational Graph Clustering
• Seq-HGNN: Learning Sequential Node Representation on Heterogeneous Graph
• Graph Learning for Combinatorial Optimization: A Survey of State-of-the-Art
• Heterogeneous Graph Representation of Stiffened Panels with Non-Uniform Boundary Conditions and Loads
• Heterogeneous Similarity Graph Neural Network on Electronic Health Records
• FCS-HGNN: Flexible Multi-type Community Search in Heterogeneous Information Networks
• Metapath- and Entity-aware Graph Neural Network for Recommendation
• Tree Structure-Aware Graph Representation Learning via Integrated Hierarchical Aggregation and Relational Metric Learning
• Structure-Aware Hard Negative Mining for Heterogeneous Graph Contrastive Learning
• HetFS: A Method for Fast Similarity Search with Ad-hoc Meta-paths on Heterogeneous Information Networks
• Leveraging Meta-path Contexts for Classification in Heterogeneous Information Networks
• Concept-Aware Denoising Graph Neural Network for Micro-Video Recommendation
• When Heterophily Meets Heterogeneity: Challenges and a New Large-Scale Graph Benchmark
• Adaptive Neural Message Passing for Inductive Learning on Hypergraphs
• HeMI: Multi-view Embedding in Heterogeneous Graphs
• GCN for HIN via Implicit Utilization of Attention and Meta-paths
• ${\text{H}}^2\text{TNE}$: Temporal Heterogeneous Information Network Embedding in Hyperbolic Spaces
• Multi-Hyperbolic Space-based Heterogeneous Graph Attention Network
• Virtual Nodes based Heterogeneous Graph Convolutional Neural Network for Efficient Long-Range Information Aggregation
• Semi-Disentangled Representation Learning in Recommendation System
• PanRep: Graph neural networks for extracting universal node embeddings in heterogeneous graphs
• Attributed Graph Clustering in Collaborative Settings
• Data-Driven Self-Supervised Graph Representation Learning
• Heterogeneous Graph Neural Network with Multi-view Representation Learning
• TEA: A Sequential Recommendation Framework via Temporally Evolving Aggregations
• A Literature Review of Recent Graph Embedding Techniques for Biomedical Data
• Analysis of 5G academic Network based on graph representation learning method
• GAHNE: Graph-Aggregated Heterogeneous Network Embedding
• Multi-Class and Multi-Task Strategies for Neural Directed Link Prediction
• AMinerGNN: Heterogeneous Graph Neural Network for Paper Click-through Rate Prediction with Fusion Query
• Optimizing Graph Transformer Networks with Graph-based Techniques