UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks

Hypergraph, an expressive structure with flexibility to model the higher-order correlations among entities, has recently attracted increasing attention from various research domains. Despite the success of Graph Neural Networks (GNNs) for graph representation learning, how to adapt the powerful GNN-variants directly into hypergraphs remains a challenging problem. In this paper, we propose UniGNN, a unified framework for interpreting the message passing process in graph and hypergraph neural networks, which can generalize general GNN models into hypergraphs. In this framework, meticulously-designed architectures aiming to deepen GNNs can also be incorporated into hypergraphs with the least effort. Extensive experiments have been conducted to demonstrate the effectiveness of UniGNN on multiple real-world datasets, which outperform the state-of-the-art approaches with a large margin. Especially for the DBLP dataset, we increase the accuracy from 77.4% to 88.8% in the semi-supervised hypernode classification task. We further prove that the proposed message-passing based UniGNN models are at most as powerful as the 1-dimensional Generalized Weisfeiler-Leman (1-GWL) algorithm in terms of distinguishing non-isomorphic hypergraphs. Our code is available at https://github.com/OneForward/UniGNN.

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

[2]  Ken-ichi Kawarabayashi,et al.  Representation Learning on Graphs with Jumping Knowledge Networks , 2018, ICML.

[3]  Xiangliang Zhang,et al.  Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation , 2020, AAAI.

[4]  M. Brešar.  Homomorphisms , 2019, Springer Undergraduate Mathematics Series.

[5]  I. Tsang,et al.  Graph Cross Networks with Vertex Infomax Pooling , 2020, NeurIPS.

[6]  Christopher Morris,et al.  Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings , 2020, NeurIPS.

[7]  Partha Pratim Talukdar,et al.  HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs , 2018 .

[8]  Yaliang Li,et al.  Simple and Deep Graph Convolutional Networks , 2020, ICML.

[9]  Pei Lv,et al.  Semi-Dynamic Hypergraph Neural Network for 3D Pose Estimation , 2020, IJCAI.

[10]  Lise Getoor,et al.  Collective Classification in Network Data , 2008, AI Mag..

[11]  Jure Leskovec,et al.  How Powerful are Graph Neural Networks? , 2018, ICLR.

[12]  Naganand Yadati,et al.  Neural Message Passing for Multi-Relational Ordered and Recursive Hypergraphs , 2020, NeurIPS.

[13]  Martin Grohe,et al.  Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks , 2018, AAAI.

[14]  Marcel Worring,et al.  HyperSAGE: Generalizing Inductive Representation Learning on Hypergraphs , 2020, ArXiv.

[15]  Shaoyi Du,et al.  Hypergraph Learning: Methods and Practices , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Yixin Chen,et al.  Link Prediction Based on Graph Neural Networks , 2018, NeurIPS.

[17]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

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

[19]  Jan Boker,et al.  Color Refinement, Homomorphisms, and Hypergraphs , 2019, 1903.12432.

[20]  Yue Gao,et al.  Hypergraph Neural Networks , 2018, AAAI.

[21]  Mario Krenn,et al.  Quantum experiments and hypergraphs: Multiphoton sources for quantum interference, quantum computation, and quantum entanglement , 2020 .

[22]  J. Leskovec,et al.  Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning , 2020, NeurIPS.

[23]  Xiao Huang,et al.  Towards Deeper Graph Neural Networks with Differentiable Group Normalization , 2020, NeurIPS.

[24]  Song Bai,et al.  Hypergraph Convolution and Hypergraph Attention , 2019, Pattern Recognit..