A Hypergraph Neural Network Framework for Learning Hyperedge-Dependent Node Embeddings

In this work, we introduce a hypergraph representation learning framework called Hypergraph Neural Networks (HNN) that jointly learns hyperedge embeddings along with a set of hyperedge-dependent embeddings for each node in the hypergraph. HNN derives multiple embeddings per node in the hypergraph where each embedding for a node is dependent on a specific hyperedge of that node. Notably, HNN is accurate, data-efficient, flexible with many interchangeable components, and useful for a wide range of hypergraph learning tasks. We evaluate the effectiveness of the HNN framework for hyperedge prediction and hypergraph node classification. We find that HNN achieves an overall mean gain of 7.72% and 11.37% across all baseline models and graphs for hyperedge prediction and hypergraph node classification, respectively.

[1]  Baocai Yin,et al.  Multitask Hypergraph Convolutional Networks: A Heterogeneous Traffic Prediction Framework , 2022, IEEE Transactions on Intelligent Transportation Systems.

[2]  R. Ji,et al.  Generating Hypergraph-Based High-Order Representations of Whole-Slide Histopathological Images for Survival Prediction , 2022, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Zizhao Zhang,et al.  Deep Hypergraph Structure Learning , 2022, ArXiv.

[4]  Yong Li,et al.  Enhancing Hypergraph Neural Networks with Intent Disentanglement for Session-based Recommendation , 2022, SIGIR.

[5]  Jiashu Zhao,et al.  Hypergraph Contrastive Collaborative Filtering , 2022, SIGIR.

[6]  Ryan A. Rossi,et al.  VisGNN: Personalized Visualization Recommendationvia Graph Neural Networks , 2022, WWW.

[7]  J. M. Thomas,et al.  Graph Neural Networks Designed for Different Graph Types: A Survey , 2022, Trans. Mach. Learn. Res..

[8]  Yatao Bian,et al.  Hypergraph Convolutional Networks via Equivalency between Hypergraphs and Undirected Graphs , 2022, ArXiv.

[9]  V. Moscato,et al.  Music Recommendation via Hypergraph Embedding , 2022, IEEE Transactions on Neural Networks and Learning Systems.

[10]  Marc Brockschmidt,et al.  HEAT: Hyperedge Attention Networks , 2022, Trans. Mach. Learn. Res..

[11]  Shirui Pan,et al.  Hypergraph Convolutional Network for Group Recommendation , 2021, 2021 IEEE International Conference on Data Mining (ICDM).

[12]  Marcel Worring,et al.  Adaptive Neural Message Passing for Inductive Learning on Hypergraphs , 2021, ArXiv.

[13]  Dongjie Zhu,et al.  Motifs-based recommender system via hypergraph convolution and contrastive learning , 2021, Neurocomputing.

[14]  O. Milenkovic,et al.  You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks , 2022, ICLR.

[15]  Shu-Tao Xia,et al.  Learnable Hypergraph Laplacian for Hypergraph Learning , 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[16]  Muhan Zhang,et al.  Principled Hyperedge Prediction with Structural Spectral Features and Neural Networks , 2021, ArXiv.

[17]  Yue Gao,et al.  Multi-Scale Representation Learning on Hypergraph for 3D Shape Retrieval and Recognition , 2021, IEEE Transactions on Image Processing.

[18]  Jing Huang,et al.  UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks , 2021, IJCAI.

[19]  Sajid Javed,et al.  Colorectal Cancer Tissue Classification Using Semi-Supervised Hypergraph Convolutional Network , 2021, 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI).

[20]  Tong Chen,et al.  DDHH: A Decentralized Deep Learning Framework for Large-scale Heterogeneous Networks , 2021, 2021 IEEE 37th International Conference on Data Engineering (ICDE).

[21]  Austin R. Benson,et al.  A nonlinear diffusion method for semi-supervised learning on hypergraphs , 2021, ArXiv.

[22]  Xiangliang Zhang,et al.  Hierarchical Hyperedge Embedding-Based Representation Learning for Group Recommendation , 2021, ACM Trans. Inf. Syst..

[23]  Qionghai Dai,et al.  Heterogeneous Hypergraph Variational Autoencoder for Link Prediction , 2021, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Hansheng Xue,et al.  Multiplex Bipartite Network Embedding using Dual Hypergraph Convolutional Networks , 2021, WWW.

[25]  Jie Li,et al.  Hypergraph Neural Network for Skeleton-Based Action Recognition , 2021, IEEE Transactions on Image Processing.

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

[27]  Xu Chen,et al.  Neural Feature-aware Recommendation with Signed Hypergraph Convolutional Network , 2020, ACM Trans. Inf. Syst..

[28]  Gustav Sourek,et al.  Learning with Molecules beyond Graph Neural Networks , 2020, ArXiv.

[29]  Bo Liu,et al.  Heterogeneous Hypergraph Embedding for Graph Classification , 2020, WSDM.

[30]  Anand Louis,et al.  NHP: Neural Hypergraph Link Prediction , 2020, CIKM.

[31]  Wei Li,et al.  AdaHGNN: Adaptive Hypergraph Neural Networks for Multi-Label Image Classification , 2020, ACM Multimedia.

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

[33]  James Caverlee,et al.  Next-item Recommendation with Sequential Hypergraphs , 2020, SIGIR.

[34]  Jinkyoo Park,et al.  Hypergraph Convolutional Recurrent Neural Network , 2020, KDD.

[35]  D. Poole,et al.  Metric Learning in Optimal Transport for Domain Adaptation , 2020, IJCAI.

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

[37]  Yoshua Bengio,et al.  HNHN: Hypergraph Networks with Hyperedge Neurons , 2020, ArXiv.

[38]  Jie Yang,et al.  LBSN2Vec++: Heterogeneous Hypergraph Embedding for Location-Based Social Networks , 2020, IEEE Transactions on Knowledge and Data Engineering.

[39]  Xiangnan He,et al.  LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation , 2020, SIGIR.

[40]  Bo Liu,et al.  Co-Detection of crowdturfing microblogs and spammers in online social networks , 2019, World Wide Web.

[41]  Yue Gao,et al.  Dynamic Hypergraph Neural Networks , 2019, IJCAI.

[42]  Liujuan Cao,et al.  Hypergraph Induced Convolutional Manifold Networks , 2019, IJCAI.

[43]  Benjamin J Raphael,et al.  Random Walks on Hypergraphs with Edge-Dependent Vertex Weights , 2019, ICML.

[44]  Bofeng Zhang,et al.  Personalized recommendation based on hierarchical interest overlapping community , 2019, Inf. Sci..

[45]  Yuan He,et al.  Graph Neural Networks for Social Recommendation , 2019, WWW.

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

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

[48]  Ryan A. Rossi,et al.  Higher-order Graph Convolutional Networks , 2018, ArXiv.

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

[50]  Song-Chun Zhu,et al.  Learning Human-Object Interactions by Graph Parsing Neural Networks , 2018, ECCV.

[51]  Ryan A. Rossi,et al.  Attention Models in Graphs: A Survey , 2018 .

[52]  Yue Gao,et al.  Dynamic Hypergraph Structure Learning , 2018, IJCAI.

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

[54]  Marcel Worring,et al.  Exploiting Relational Information in Social Networks using Geometric Deep Learning on Hypergraphs , 2018, ICMR.

[55]  Yixin Chen,et al.  Beyond Link Prediction: Predicting Hyperlinks in Adjacency Space , 2018, AAAI.

[56]  Yiqun Liu,et al.  Learning on Partial-Order Hypergraphs , 2018, WWW.

[57]  Geoffrey Ye Li,et al.  Hypergraph Theory: Applications in 5G Heterogeneous Ultra-Dense Networks , 2017, IEEE Communications Magazine.

[58]  Max Welling,et al.  Graph Convolutional Matrix Completion , 2017, ArXiv.

[59]  Ryan A. Rossi,et al.  Deep Feature Learning for Graphs , 2017, ArXiv.

[60]  Khalil Sima'an,et al.  Graph Convolutional Encoders for Syntax-aware Neural Machine Translation , 2017, EMNLP.

[61]  Daniel R. Figueiredo,et al.  struc2vec: Learning Node Representations from Structural Identity , 2017, KDD.

[62]  Predrag Radivojac,et al.  Classification in biological networks with hypergraphlet kernels , 2017, Bioinform..

[63]  Deng Cai,et al.  Heterogeneous hypergraph embedding for document recommendation , 2016, Neurocomputing.

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

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

[66]  Balaraman Ravindran,et al.  Extended Discriminative Random Walk: A Hypergraph Approach to Multi-View Multi-Relational Transductive Learning , 2015, IJCAI.

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

[68]  Dong Li,et al.  Link prediction in social networks based on hypergraph , 2013, WWW.

[69]  Tan Zhang,et al.  On Spectral Hypergraph Theory of the Adjacency Tensor , 2012, Graphs Comb..

[70]  Jure Leskovec,et al.  Defining and evaluating network communities based on ground-truth , 2012, Knowledge and Information Systems.

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

[72]  Bernhard Schölkopf,et al.  Learning with Hypergraphs: Clustering, Classification, and Embedding , 2006, NIPS.

[73]  J. Renders,et al.  Joint Personalized Search and Recommendation with Hypergraph Convolutional Networks , 2022, ECIR.

[74]  Ryan A. Rossi,et al.  An Interpretable Graph Generative Model with Heterophily , 2021, ArXiv.

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

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

[77]  Ryan A. Rossi,et al.  role2vec: Role-based Network Embeddings , 2019 .