Relation Structure-Aware Heterogeneous Graph Neural Network

Heterogeneous graphs with different types of nodes and edges are ubiquitous and have immense value in many applications. Existing works on modeling heterogeneous graphs usually follow the idea of splitting a heterogeneous graph into multiple homogeneous subgraphs. This is ineffective in exploiting hidden rich semantic associations between different types of edges for large-scale multi-relational graphs. In this paper, we propose Relation Structure-Aware Heterogeneous Graph Neural Network (RSHN), a unified model that integrates graph and its coarsened line graph to embed both nodes and edges in heterogeneous graphs without requiring any prior knowledge such as metapath. To tackle the heterogeneity of edge connections, RSHN first creates a Coarsened Line Graph Neural Network (CL-GNN) to excavate edge-centric relation structural features that respect the latent associations of different types of edges based on coarsened line graph. After that, a Heterogeneous Graph Neural Network (H-GNN) is used to leverage implicit messages from neighbor nodes and edges propagating among nodes in heterogeneous graphs. As a result, different types of nodes and edges can enhance their embedding through mutual integration and promotion. Experiments and comparisons, based on semi-supervised classification tasks on large scale heterogeneous networks with over a hundred types of edges, show that RSHN significantly outperforms state-of-the-arts.

[1]  Stephan Bloehdorn,et al.  Kernel Methods for Mining Instance Data in Ontologies , 2007, ISWC/ASWC.

[2]  Johannes Fürnkranz,et al.  Unsupervised generation of data mining features from linked open data , 2012, WIMS '12.

[3]  Charu C. Aggarwal,et al.  Heterogeneous Network Embedding via Deep Architectures , 2015, KDD.

[4]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[5]  Heiko Paulheim,et al.  RDF2Vec: RDF Graph Embeddings for Data Mining , 2016, SEMWEB.

[6]  Steven de Rooij,et al.  Substructure counting graph kernels for machine learning from RDF data , 2015, J. Web Semant..

[7]  Alán Aspuru-Guzik,et al.  Convolutional Networks on Graphs for Learning Molecular Fingerprints , 2015, NIPS.

[8]  Max Welling,et al.  Modeling Relational Data with Graph Convolutional Networks , 2017, ESWC.

[9]  Samuel S. Schoenholz,et al.  Neural Message Passing for Quantum Chemistry , 2017, ICML.

[10]  Joan Bruna,et al.  Community Detection with Graph Neural Networks , 2017, 1705.08415.

[11]  Jing Jiang,et al.  Graph WaveNet for Deep Spatial-Temporal Graph Modeling , 2019, IJCAI.

[12]  Yanfang Ye,et al.  Heterogeneous Graph Attention Network , 2019, WWW.

[13]  Shanshan Li,et al.  Deep Collective Classification in Heterogeneous Information Networks , 2018, WWW.

[14]  Jiawei Han,et al.  Meta-Path Guided Embedding for Similarity Search in Large-Scale Heterogeneous Information Networks , 2016, ArXiv.

[15]  Zhiyuan Liu,et al.  Graph Neural Networks: A Review of Methods and Applications , 2018, AI Open.

[16]  Yang Zhang,et al.  Efficient Metropolitan Traffic Prediction Based on Graph Recurrent Neural Network , 2018, ArXiv.

[17]  Philip S. Yu,et al.  A Comprehensive Survey on Graph Neural Networks , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[18]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[19]  Jason Weston,et al.  Translating Embeddings for Modeling Multi-relational Data , 2013, NIPS.

[20]  Chengqi Zhang,et al.  Learning Graph Embedding With Adversarial Training Methods , 2019, IEEE Transactions on Cybernetics.

[21]  Yizhou Sun,et al.  Semi-supervised Learning over Heterogeneous Information Networks by Ensemble of Meta-graph Guided Random Walks , 2017, IJCAI.

[22]  Yizhou Sun,et al.  Mining heterogeneous information networks: a structural analysis approach , 2013, SKDD.

[23]  Yuji Matsumoto,et al.  Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approach , 2017, ArXiv.

[24]  Steven de Rooij,et al.  A Fast and Simple Graph Kernel for RDF , 2013, DMoLD.

[25]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[26]  Antoine Isaac,et al.  Supporting Linked Data Production for Cultural Heritage Institutes: The Amsterdam Museum Case Study , 2012, ESWC.