Heterogeneous Graph Attention Network
Графовая нейронная сеть с механизмом внимания для неоднородных графов
2019-05-13
SCID: 54.1/j9vdkjuc
Discuss with AI
heterogeneous graph attention networkhierarchical attentionmeta-path based neighborsnode embeddingsemantic-level attention
Figures from the paper
Abstract (AI)
Graph neural network, as a powerful graph representation technique based on deep learning, has shown superior performance and attracted considerable research interest. However, it has not been fully considered in graph neural network for heterogeneous graph which contains different types of nodes and links. The heterogeneity and rich semantic information bring great challenges for designing a graph neural network for heterogeneous graph. Recently, one of the most exciting advancements in deep learning is the attention mechanism, whose great potential has been well demonstrated in various areas. In this paper, we first propose a novel heterogeneous graph neural network based on the hierarchical attention, including node-level and semantic-level attentions. Specifically, the node-level attention aims to learn the importance between a node and its meta-path based neighbors, while the semantic-level attention is able to learn the importance of different meta-paths. With the learned importance from both node-level and semantic-level attention, the importance of node and meta-path can be fully considered. Then the proposed model can generate node embedding by aggregating features from meta-path based neighbors in a hierarchical manner. Extensive experimental results on three real-world heterogeneous graphs not only show the superior performance of our proposed model over the state-of-the-arts, but also demonstrate its potentially good interpretability for graph analysis.
Key Findings
1
Experiments on three real-world heterogeneous graphs show superior performance over state-of-the-art methods and indicate potentially strong interpretability for graph analysis.
2
Introduces a heterogeneous graph neural network using hierarchical attention with separate node-level and semantic-level attention mechanisms.
3
Node-level attention learns the importance of individual meta-path-based neighbors relative to a target node.
4
Semantic-level attention learns the relative importance of different meta-paths, enabling semantic information to influence aggregation.
5
The model generates node embeddings by hierarchically aggregating features from meta-path-based neighbors using both learned importance weights.
Research Object
Heterogeneous graphs with different node and link types and meta-path-based neighborhoods
Research Subject
Hierarchical attention-based representation learning, including node-level and semantic-level importance of neighbors and meta-paths for node embedding and interpretable graph analysis
Publication Details
Publication Date
2019-05-13
Journal
Publisher
ISSN
Cited by
3188
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai5
Exploiting Generative AI to Scale up Intelligent Tutoring Systems2023
Semi-Supervised Classification with Graph Convolutional Networks2016
The Graph Neural Network Model2008
Data Driven VRP: A Neural Network Model to Learn Hidden Preferences for VRP2021
Targeted Branching for the Maximum Independent Set Problem Using Graph Neural Networks2024
Cited by16
A Comprehensive Survey on Graph Neural Networks2020
Graph neural networks: A review of methods and applications2020
Heterogeneous Graph Transformer2020
Knowledge Graphs2021
Deep Learning on Graphs: A Survey2020
Graph Neural Networks: A Review of Methods and Applications2018
Graph Neural Networks in Recommender Systems: A Survey2022
MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding2020
A Survey on Graph Representation Learning Methods2023
Graph Neural Networks for Intrusion Detection: A Survey2023
Anomaly Detection in Dynamic Graphs: A Comprehensive Survey2024
A Survey on Malware Detection with Graph Representation Learning2024
User Response Prediction in Online Advertising2021
Graph neural networks: a survey on the links between privacy and security2024
Spatial-Temporal-Aware Graph Transformer for Transaction Fraud Detection2024
Graph Neural Networks for Modeling Complex Dependencies in Global Supply Chain Networks2026