skip to main content
10.1145/3340531.3411870acmconferencesArticle/Chapter ViewAbstractPublication PagescikmConference Proceedingsconference-collections
research-article

NHP: Neural Hypergraph Link Prediction

Published: 19 October 2020 Publication History

Abstract

Link prediction insimple graphs is a fundamental problem in which new links between vertices are predicted based on the observed structure of the graph. However, in many real-world applications, there is a need to model relationships among vertices that go beyond pairwise associations. For example, in a chemical reaction, relationship among the reactants and products is inherently higher-order. Additionally, there is a need to represent the direction from reactants to products. Hypergraphs provide a natural way to represent such complex higher-order relationships. Graph Convolutional Network (GCN) has recently emerged as a powerful deep learning-based approach for link prediction over simple graphs. However, their suitability for link prediction in hypergraphs is underexplored -- we fill this gap in this paper and propose Neural Hyperlink Predictor (NHP). NHP adapts GCNs for link prediction in hypergraphs. We propose two variants of NHP -- NHP-U and NHP-D -- for link prediction over undirected and directed hypergraphs, respectively. To the best of our knowledge, NHP-D is the first-ever method for link prediction over directed hypergraphs. An important feature of NHP is that it can also be used for hyperlinks in which dissimilar vertices interact (e.g. acids reacting with bases). Another attractive feature of NHP is that it can be used to predict unseen hyperlinks at test time (inductive hyperlink prediction). Through extensive experiments on multiple real-world datasets, we show NHP's effectiveness.

Supplementary Material

MP4 File (3340531.3411870.mp4)
Video Presentation of NHP: Neural Hypergraph Link Prediction

References

[1]
Devanshu Arya and Marcel Worring. 2018. Exploiting Relational Information in Social Networks Using Geometric Deep Learning on Hypergraphs. In ICMR.
[2]
Haoli Bai, Zhuangbin Chen, Michael R. Lyu, Irwin King, and Zenglin Xu. 2018. Neural Relational Topic Models for Scientific Article Analysis. In CIKM.
[3]
Peter W. Battaglia, Jessica B. Hamrick, Victor Bapst, Alvaro Sanchez-Gonzalez, Vin'i cius Flores Zambaldi, Mateusz Malinowski, Andrea Tacchetti, David Raposo, Adam Santoro, Ryan Faulkner, cC aglar Gü lcc ehre, Francis Song, Andrew J. Ballard, Justin Gilmer, George E. Dahl, Ashish Vaswani, Kelsey Allen, Charles Nash, Victoria Langston, Chris Dyer, Nicolas Heess, Daan Wierstra, Pushmeet Kohli, Matthew Botvinick, Oriol Vinyals, Yujia Li, and Razvan Pascanu. 2018. Relational inductive biases, deep learning, and graph networks. CoRR, arXiv:1806.01261 (2018).
[4]
Inci M Baytas, Cao Xiao, Fei Wang, Anil K. Jain, and Jiayu Zhou. 2018. HHNE: Heterogeneous Hyper-Network Embedding. In IEEE International Conference on Data Mining (ICDM). 875--880.
[5]
Michael M. Bronstein, Joan Bruna, Yann LeCun, Arthur Szlam, and Pierre Vandergheynst. 2017. Geometric Deep Learning: Going beyond Euclidean data. IEEE Signal Process. Mag. (2017).
[6]
T.-H. Hubert Chan, Zhihao Gavin Tang, Xiaowei Wu, and Chenzi Zhang. 2019. Diffusion operator and spectral analysis for directed hypergraph Laplacian. Theor. Comput. Sci. (TCS), Vol. 784 (2019), 46--64.
[7]
T.-H. Hubert Chan, Anand Louis, Zhihao Gavin Tang, and Chenzi Zhang. 2018. Spectral Properties of Hypergraph Laplacian and Approximation Algorithms. J. ACM (2018).
[8]
Se eun Yoon, Hyungseok Song, Kijung Shin, and Yung Yi. 2020. How Much and When Do We Need Higher-order Information in Hypergraphs? A Case Study on Hyperedge Prediction. In Proceedings of the 29th International Conference on World Wide Web (WWW).
[9]
Bahare Fatemi, Perouz Taslakian, David Vazquez, and David Poole. 2020. Knowledge Hypergraphs: Prediction Beyond Binary Relations. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI).
[10]
Yifan Feng, Haoxuan You, Zizhao Zhang, Rongrong Ji, and Yue Gao. 2019. Hypergraph Neural Networks. In Proceedings of the Thirty-Third Conference on Association for the Advancement of Artificial Intelligence (AAAI). 3558--3565.
[11]
Luis Galárraga, Geremy Heitz, Kevin Murphy, and Fabian M. Suchanek. 2014. Canonicalizing Open Knowledge Bases. In Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management (CIKM). 1679----1688.
[12]
Giorgio Gallo, Giustino Longo, Stefano Pallottino, and Sang Nguyen. 1993. Directed Hypergraphs and Applications. Discrete Appl. Math. (1993).
[13]
Justin Gilmer, Samuel S. Schoenholz, Patrick F. Riley, Oriol Vinyals, and George E. Dahl. 2017. Neural Message Passing for Quantum Chemistry. In ICML.
[14]
Aditya Grover and Jure Leskovec. 2016. Node2Vec: Scalable Feature Learning for Networks. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). 855----864.
[15]
William L. Hamilton, Rex Ying, and Jure Leskovec. 2017a. Inductive Representation Learning on Large Graphs. In NIPS.
[16]
William L. Hamilton, Rex Ying, and Jure Leskovec. 2017b. Representation Learning on Graphs: Methods and Applications. IEEE Data Eng. Bull. (2017).
[17]
Jie Huang, Xin Liu, and Yangqiu Song. 2019. Hyper-Path-Based Representation Learning for Hyper-Networks. In Proceedings of the Conference on Information and Knowledge Management (CIKM).
[18]
Wengong Jin, Connor Coley, Regina Barzilay, and Tommi Jaakkola. 2017. Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network. In NIPS.
[19]
Thomas N Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In International Conference on Learning Representations (ICLR).
[20]
Linyuan Lü and Tao Zhou. 2011. Link prediction in complex networks: A survey. Physica A: Statistical Mechanics and its Applications (2011).
[21]
Dong Li, Zhiming Xu, Sheng Li, and Xin Sun. 2013. Link Prediction in Social Networks Based on Hypergraph. In WWW.
[22]
Pan Li, Niao He, and Olgica Milenkovic. 2018. Quadratic Decomposable Submodular Function Minimization. In Advances in Neural Information Processing Systems (NeurIPS) 31. Curran Associates, Inc., 1054--1064.
[23]
Pan Li and Olgica Milenkovic. 2017. Inhomogeneous Hypergraph Clustering with Applications. In Advances in Neural Information Processing Systems (NeurIPS) 30. Curran Associates, Inc., 2308--2318.
[24]
Pan Li and Olgica Milenkovic. 2018. Submodular Hypergraphs: p-Laplacians, Cheeger Inequalities and Spectral Clustering. In Proceedings of the 35th International Conference on Machine Learning (ICML). 3014--3023.
[25]
David Liben-Nowell and Jon Kleinberg. 2003. The Link Prediction Problem for Social Networks. In CIKM.
[26]
Yashu Liu, Shuang Qiu, Ping Zhang, Pinghua Gong, Fei Wang, Guoliang Xue, and Jieping Ye. 2017. Computational Drug Discovery with Dyadic Positive-Unlabeled Learning. In Proceedings of the 2017 SIAM International Conference on Data Mining.
[27]
Anand Louis. 2015. Hypergraph Markov Operators, Eigenvalues, Approximation Algorithms. In STOC.
[28]
Federico Monti, Michael Bronstein, and Xavier Bresson. 2017. Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks. In NIPS.
[29]
Maximilian Nickel, Kevin Murphy, Volker Tresp, and Evgeniy Gabrilovich. 2016. A Review of Relational Machine Learning for Knowledge Graphs. Proc. IEEE (2016).
[30]
Vinay Satish Kumar, Madhukar S. Dasika, and Costas D. Maranas. 2007. Optimization based automated curation of metabolic reconstructions. BMC Bioinformatics (2007).
[31]
Ke Tu, Peng Cui, Xiao Wang, Fei Wang, and Wenwu Zhu. 2018. Structural Deep Embedding for Hyper-Networks. In Proceedings of the Thirty-Third Conference on Association for the Advancement of Artificial Intelligence (AAAI). 426--433.
[32]
Shikhar Vashishth, Prince Jain, and Partha Talukdar. 2018. CESI: Canonicalizing Open Knowledge Bases Using Embeddings and Side Information. In Proceedings of the 2018 World Wide Web Conference (WWW). 1317----1327.
[33]
Shikhar Vashishth, Prateek Yadav, Manik Bhandari, and Partha Talukdar. 2019. Confidence-based Graph Convolutional Networks for Semi-Supervised Learning. In International Conference on Artificial Intelligence and Statistics (AISTATS).
[34]
Petar Velivc ković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph Attention Networks. In ICLR.
[35]
Petar Velivc ković, William Fedus, William L. Hamilton, Pietro Lió, Yoshua Bengio, and R Devon Hjelm. 2019. Deep Graph Infomax. In International Confernece on Learning Representations (ICLR).
[36]
B. L. Welch. 1947. The Generalization of 'Student's' Problem when Several Different Population Variances are Involved. Biometrika, Vol. 34, 1/2 (1947), 28--35. http://www.jstor.org/stable/2332510
[37]
Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, and Philip S. Yu. 2019. A Comprehensive Survey on Graph Neural Networks. CoRR, arXiv:1901.00596 (2019).
[38]
Naganand Yadati, Madhav Nimishakavi, Prateek Yadav, Vikram Nitin, Anand Louis, and Partha Talukdar. 2019. HyperGCN: A New Method For Training Graph Convolutional Networks on Hypergraphs. In Advances in Neural Information Processing Systems (NeurIPS) 32. Curran Associates, Inc., 1509--1520.
[39]
Chia-An Yu, Ching-Lun Tai, Tak-Shing Chan, and Yi-Hsuan Yang. 2018. Modeling Multi-Way Relations with Hypergraph Embedding. In Proceedings of the Conference on Information and Knowledge Management (CIKM). 1707----1710.
[40]
Chenzi Zhang, Shuguang Hu, Zhihao Gavin Tang, and T-H. Hubert Chan. 2017. Re-revisiting Learning on Hypergraphs: Confidence Interval and Subgradient Method. In Proceedings of the 34th International Conference on Machine Learning (ICML). 4026--4034.
[41]
Muhan Zhang and Yixin Chen. 2018. Link Prediction Based on Graph Neural Networks. In Advances in Neural Information Processing Systems (NeurIPS) 31. Curran Associates, Inc., 5171--5181.
[42]
Muhan Zhang, Zhicheng Cui, Shali Jiang, and Yixin Chen. 2018. Beyond Link Prediction: Predicting Hyperlinks in Adjacency Space. In Proceedings of the Thirty-Second Conference on Association for the Advancement of Artificial Intelligence (AAAI). 4430--4437.
[43]
Ruochi Zhang, Yuesong Zou, and Jian Ma. 2020. Hyper-SAGNN: a self-attention based graph neural network for hypergraphs. In International Confernece on Learning Representations (ICLR).
[44]
Dengyong Zhou, Jiayuan Huang, and Bernhard Schö lkopf. 2006. Learning with Hypergraphs: Clustering, Classification, and Embedding. In Proceedings of the 19th International Conference on Neural Information Processing Systems (NeurIPS).

Cited By

View all
  • (2025)Census and Analysis of Higher-Order Interactions in Real-World HypergraphsBig Data Mining and Analytics10.26599/BDMA.2024.90200918:2(383-406)Online publication date: Apr-2025
  • (2025)Physics-Guided Hypergraph Contrastive Learning for Dynamic Hyperedge PredictionIEEE Transactions on Network Science and Engineering10.1109/TNSE.2024.350137812:1(433-450)Online publication date: Jan-2025
  • (2025)Directed Link Prediction Using GNN With Local and Global Feature FusionIEEE Transactions on Network Science and Engineering10.1109/TNSE.2024.349843412:1(409-422)Online publication date: Jan-2025
  • Show More Cited By

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
CIKM '20: Proceedings of the 29th ACM International Conference on Information & Knowledge Management
October 2020
3619 pages
ISBN:9781450368599
DOI:10.1145/3340531
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 19 October 2020

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. directed hypergraph
  2. graph neural network
  3. knowledge graph canonicalisation
  4. link prediction

Qualifiers

  • Research-article

Funding Sources

  • Ministry of Human Resource Development
  • SERB Award
  • Pratiksha Trust Young Investigator Award

Conference

CIKM '20
Sponsor:

Acceptance Rates

Overall Acceptance Rate 1,861 of 8,427 submissions, 22%

Upcoming Conference

CIKM '25

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)287
  • Downloads (Last 6 weeks)27
Reflects downloads up to 12 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2025)Census and Analysis of Higher-Order Interactions in Real-World HypergraphsBig Data Mining and Analytics10.26599/BDMA.2024.90200918:2(383-406)Online publication date: Apr-2025
  • (2025)Physics-Guided Hypergraph Contrastive Learning for Dynamic Hyperedge PredictionIEEE Transactions on Network Science and Engineering10.1109/TNSE.2024.350137812:1(433-450)Online publication date: Jan-2025
  • (2025)Directed Link Prediction Using GNN With Local and Global Feature FusionIEEE Transactions on Network Science and Engineering10.1109/TNSE.2024.349843412:1(409-422)Online publication date: Jan-2025
  • (2025)Dual-View Desynchronization Hypergraph Learning for Dynamic Hyperedge PredictionIEEE Transactions on Knowledge and Data Engineering10.1109/TKDE.2024.350902437:2(597-612)Online publication date: Feb-2025
  • (2025)Link Prediction in Complex Hyper-Networks Leveraging HyperCentralityIEEE Access10.1109/ACCESS.2025.353024513(12239-12254)Online publication date: 2025
  • (2025)Counterfactual learning for higher-order relation prediction in heterogeneous information networksNeural Networks10.1016/j.neunet.2024.107024183(107024)Online publication date: Mar-2025
  • (2025)I2HGNN: Iterative Interpretable HyperGraph Neural Network for semi-supervised classificationNeural Networks10.1016/j.neunet.2024.106929183(106929)Online publication date: Mar-2025
  • (2025)Hypergraph contrastive attention networks for hyperedge prediction with negative samples evaluationNeural Networks10.1016/j.neunet.2024.106807181(106807)Online publication date: Jan-2025
  • (2025)Learning accurate neighborhood- and self-information for higher-order relation prediction in Heterogeneous Information NetworksNeurocomputing10.1016/j.neucom.2024.128739613(128739)Online publication date: Jan-2025
  • (2025)Multi-HGNN: Multi-modal hypergraph neural networks for predicting missing reactions in metabolic networksInformation Sciences10.1016/j.ins.2025.121960(121960)Online publication date: Feb-2025
  • Show More Cited By

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media