MR-GCN: Multi-Relational Graph Convolutional Networks based on Generalized Tensor Product

Graph Convolutional Networks (GCNs) have been extensively studied in recent years. Most of existing GCN approaches are designed for the homogenous graphs with a single type of relation. However, heterogeneous graphs of multiple types of relations are also ubiquitous and there is a lack of methodologies to tackle such graphs. Some previous studies address the issue by performing conventional GCN on each single relation and then blending their results. However, as the convolutional kernels neglect the correlations across relations, the strategy is sub-optimal. In this paper, we propose the Multi-Relational Graph Convolutional Network (MR-GCN) framework by developing a novel convolution operator on multi-relational graphs. In particular, our multi-dimension convolution operator extends the graph spectral analysis into the eigen-decomposition of a Laplacian tensor. And the eigen-decomposition is formulated with a generalized tensor product, which can correspond to any unitary transform instead of limited merely to Fourier transform. We conduct comprehensive experiments on four real-world multi-relational graphs to solve the semi-supervised node classification task, and the results show the superiority of MR-GCN against the state-of-the-art competitors.

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

[2]  Joan Bruna,et al.  Deep Convolutional Networks on Graph-Structured Data , 2015, ArXiv.

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

[4]  Jure Leskovec,et al.  node2vec: Scalable Feature Learning for Networks , 2016, KDD.

[5]  M. Kilmer,et al.  Factorization strategies for third-order tensors , 2011 .

[6]  Vasant Honavar,et al.  MEGAN: A Generative Adversarial Network for Multi-View Network Embedding , 2019, IJCAI.

[7]  Luca Cardelli,et al.  The World Wide Web Conference , 2019, WWW.

[8]  Mingzhe Wang,et al.  LINE: Large-scale Information Network Embedding , 2015, WWW.

[9]  Yunming Ye,et al.  MultiRank: co-ranking for objects and relations in multi-relational data , 2011, KDD.

[10]  Yunming Ye,et al.  Low-Rank Tensor Completion with Total Variation for Visual Data Inpainting , 2017, AAAI.

[11]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[12]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.

[13]  Audra E. Kosh,et al.  Linear Algebra and its Applications , 1992 .

[14]  Ian Davidson,et al.  Proceedings of the 2012 SIAM International Conference on Data Mining , 2012 .

[15]  Xavier Bresson,et al.  Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.

[16]  Ruslan Salakhutdinov,et al.  Revisiting Semi-Supervised Learning with Graph Embeddings , 2016, ICML.

[17]  Joan Bruna,et al.  Spectral Networks and Locally Connected Networks on Graphs , 2013, ICLR.

[18]  Mikkel N. Schmidt,et al.  Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials , 2018, NIPS 2018.

[19]  Charu C. Aggarwal,et al.  Multi-dimensional Graph Convolutional Networks , 2018, SDM.

[20]  Yunming Ye,et al.  MultiComm: Finding Community Structure in Multi-Dimensional Networks , 2014, IEEE Transactions on Knowledge and Data Engineering.

[21]  Michael K. Ng,et al.  Robust Tensor Completion Using Transformed Tensor SVD , 2019, ArXiv.

[22]  Joshua E. Blumenstock,et al.  Multi-GCN: Graph Convolutional Networks for Multi-View Networks, with Applications to Global Poverty , 2019, AAAI.

[23]  Jonathan Masci,et al.  Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Jure Leskovec,et al.  Graph Convolutional Neural Networks for Web-Scale Recommender Systems , 2018, KDD.

[25]  H. Damasio,et al.  IEEE Transactions on Pattern Analysis and Machine Intelligence: Special Issue on Perceptual Organization in Computer Vision , 1998 .