Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
skip to main content
10.1145/3485447.3512181acmconferencesArticle/Chapter ViewAbstractPublication PagesthewebconfConference Proceedingsconference-collections
research-article
Open access

Neural Predicting Higher-order Patterns in Temporal Networks

Published: 25 April 2022 Publication History

Abstract

Dynamic systems that consist of a set of interacting elements can be abstracted as temporal networks. Recently, higher-order patterns that involve multiple interacting nodes have been found crucial to indicate domain-specific laws of different temporal networks. This posts us the challenge of designing more sophisticated hypergraph models for these higher-order patterns and the associated new learning algorithms. Here, we propose the first model, named HIT, for full-spectrum higher-order pattern prediction in temporal hypergraphs. Particularly, we focus on predicting three types of common but important interaction patterns involving three interacting elements in temporal networks, which could be extended to even higher-order patterns. HIT extracts the structural representation of a node triplet of interest on the temporal hypergraph and uses it to tell what type of, when, and why the interaction expansion could happen in this triplet. HIT could achieve significant improvement (averaged 20% AUC gain to identify the interaction type, uniformly more accurate time estimation) compared to both heuristic and other neural-network-based baselines on 5 real-world large temporal hypergraphs. Moreover, HIT provides a certain degree of interpretability by identifying the most discriminatory structural features on the temporal hypergraphs for predicting different higher-order patterns.

References

[1]
Ghadeer AbuOda, Gianmarco De Francisci Morales, and Ashraf Aboulnaga. 2019. Link prediction via higher-order motif features. In ECML PKDD. Springer.
[2]
Lada A Adamic and Eytan Adar. 2003. Friends and neighbors on the web. Social networks 25, 3 (2003), 211–230.
[3]
Uri Alon. 2007. Network motifs: theory and experimental approaches. Nature Reviews Genetics 8, 6 (2007), 450–461.
[4]
Emily Alsentzer, Samuel Finlayson, Michelle Li, and Marinka Zitnik. 2020. Subgraph Neural Networks. In NeurIPS.
[5]
Sihem Amer-Yahia, Senjuti Basu Roy, Ashish Chawlat, Gautam Das, and Cong Yu. 2009. Group recommendation: Semantics and efficiency. Proceedings of the VLDB Endowment 2, 1 (2009), 754–765.
[6]
Austin R Benson, Rediet Abebe, Michael T Schaub, Ali Jadbabaie, and Jon Kleinberg. 2018. Simplicial closure and higher-order link prediction. Proceedings of the National Academy of Sciences 115, 48(2018), E11221–E11230.
[7]
Austin R Benson, David F Gleich, and Desmond J Higham. 2021. Higher-order Network Analysis Takes Off, Fueled by Classical Ideas and New Data. arXiv preprint arXiv:2103.05031(2021).
[8]
Austin R Benson, David F Gleich, and Jure Leskovec. 2016. Higher-order organization of complex networks. Science 353, 6295 (2016).
[9]
Claude Berge. 1984. Hypergraphs: combinatorics of finite sets. Vol. 45. Elsevier.
[10]
Salomon Bochner. 1992. A theorem on Fourier-Stieltjes integrals. Collected Papers of Salomon Bochner 2 (1992).
[11]
Leonardo Cotta, Carlos HC Teixeira, Ananthram Swami, and Bruno Ribeiro. 2020. Unsupervised Joint k-node Graph Representations with Compositional Energy-Based Models. In NeurIPS.
[12]
Manh Tuan Do, Se-eun Yoon, Bryan Hooi, and Kijung Shin. 2020. Structural patterns and generative models of real-world hypergraphs. In KDD.
[13]
Yifan Feng, Haoxuan You, Zizhao Zhang, Rongrong Ji, and Yue Gao. 2019. Hypergraph neural networks. In AAAI.
[14]
Dongqi Fu, Dawei Zhou, and Jingrui He. 2020. Local motif clustering on time-evolving graphs. In KDD.
[15]
Palash Goyal, Sujit Rokka Chhetri, and Arquimedes Canedo. 2020. dyngraph2vec: Capturing network dynamics using dynamic graph representation learning. Knowledge-Based Systems 187 (2020).
[16]
William L Hamilton, Rex Ying, and Jure Leskovec. 2017. Representation learning on graphs: Methods and applications. IEEE Data Engineering Bulletin 40, 3 (2017).
[17]
Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997).
[18]
Petter Holme and Jari Saramäki. 2012. Temporal networks. Physics reports 519, 3 (2012).
[19]
Jianwen Jiang, Yuxuan Wei, Yifan Feng, Jingxuan Cao, and Yue Gao. 2019. Dynamic Hypergraph Neural Networks. In IJCAI.
[20]
Seyed Mehran Kazemi, Rishab Goel, Sepehr Eghbali, Janahan Ramanan, Jaspreet Sahota, Sanjay Thakur, Stella Wu, Cathal Smyth, Pascal Poupart, and Marcus Brubaker. 2019. Time2vec: Learning a vector representation of time. arXiv preprint arXiv:1907.05321(2019).
[21]
Lauri Kovanen, Márton Karsai, Kimmo Kaski, János Kertész, and Jari Saramäki. 2011. Temporal motifs in time-dependent networks. Journal of Statistical Mechanics: Theory and Experiment (2011).
[22]
Srijan Kumar, Xikun Zhang, and Jure Leskovec. 2019. Predicting dynamic embedding trajectory in temporal interaction networks. In KDD.
[23]
Mayank Lahiri and Tanya Y Berger-Wolf. 2007. Structure prediction in temporal networks using frequent subgraphs. In CIDM.
[24]
Renaud Lambiotte, Martin Rosvall, and Ingo Scholtes. 2019. From networks to optimal higher-order models of complex systems. Nature physics 15, 4 (2019), 313–320.
[25]
Geon Lee and Kijung Shin. 2021. THyMe+: Temporal Hypergraph Motifs and Fast Algorithms for Exact Counting. arXiv preprint arXiv:2109.08341(2021).
[26]
Pan Li and Olgica Milenkovic. 2017. Inhomogeneous hypergraph clustering with applications. In NeurIPS.
[27]
Pan Li, Yanbang Wang, Hongwei Wang, and Jure Leskovec. 2020. Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning. In NeurIPS.
[28]
David Liben-Nowell and Jon Kleinberg. 2007. The link-prediction problem for social networks. Journal of the American society for information science and technology 58, 7 (2007).
[29]
Xiaoke Ma, Penggang Sun, and Yu Wang. 2018. Graph regularized nonnegative matrix factorization for temporal link prediction in dynamic networks. Physica A: Statistical mechanics and its applications 496 (2018).
[30]
Franco Manessi, Alessandro Rozza, and Mario Manzo. 2020. Dynamic graph convolutional networks. Pattern Recognition 97(2020).
[31]
Changping Meng, S Chandra Mouli, Bruno Ribeiro, and Jennifer Neville. 2018. Subgraph pattern neural networks for high-order graph evolution prediction. In AAAI.
[32]
Ron Milo, Shai Shen-Orr, Shalev Itzkovitz, Nadav Kashtan, Dmitri Chklovskii, and Uri Alon. 2002. Network motifs: simple building blocks of complex networks. Science 298, 5594 (2002), 824–827.
[33]
Huda Nassar, Austin R Benson, and David F Gleich. 2020. Neighborhood and PageRank methods for pairwise link prediction. Social Network Analysis and Mining 10, 1 (2020), 1–13.
[34]
Mark EJ Newman. 2003. The structure and function of complex networks. SIAM review 45, 2 (2003), 167–256.
[35]
Giang Hoang Nguyen, John Boaz Lee, Ryan A Rossi, Nesreen K Ahmed, Eunyee Koh, and Sungchul Kim. 2018. Continuous-time dynamic network embeddings. In WWW.
[36]
Ashwin Paranjape, Austin R Benson, and Jure Leskovec. 2017. Motifs in temporal networks. In WSDM.
[37]
Aldo Pareja, Giacomo Domeniconi, Jie Chen, Tengfei Ma, Toyotaro Suzumura, Hiroki Kanezashi, Tim Kaler, Tao B Schardl, and Charles E Leiserson. 2020. EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs. In AAAI.
[38]
José Manuel Pérez-Pérez, Héctor Candela, and José Luis Micol. 2009. Understanding synergy in genetic interactions. Trends in genetics 25, 8 (2009), 368–376.
[39]
Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. 2014. Deepwalk: Online learning of social representations. In KDD. 701–710.
[40]
H. Pishro-Nik. 2014. Introduction to Probability, Statistics, and Random Processes. Kappa Research, LLC.
[41]
Mahmudur Rahman and Mohammad Al Hasan. 2016. Link prediction in dynamic networks using graphlet. In ECML PKDD. Springer.
[42]
Emanuele Rossi, Ben Chamberlain, Fabrizio Frasca, Davide Eynard, Federico Monti, and Michael Bronstein. 2020. Temporal Graph Networks for Deep Learning on Dynamic Graphs. In ICML 2020 Workshop on Graph Representation Learning.
[43]
Ryan A Rossi, Nesreen K Ahmed, Eunyee Koh, Sungchul Kim, Anup Rao, and Yasin Abbasi Yadkori. 2018. HONE: Higher-order network embeddings. (2018).
[44]
Ryan A Rossi, Anup Rao, Sungchul Kim, Eunyee Koh, Nesreen K Ahmed, and Gang Wu. 2020. Higher-order ranking and link prediction: From closing triangles to closing higher-order motifs. In WWW.
[45]
David E Rumelhart, Geoffrey E Hinton, and Ronald J Williams. 1986. Learning representations by back-propagating errors. nature 323, 6088 (1986).
[46]
Aravind Sankar, Yanhong Wu, Liang Gou, Wei Zhang, and Hao Yang. 2020. DySAT: Deep Neural Representation Learning on Dynamic Graphs via Self-Attention Networks. In WSDM.
[47]
Georg Simmel. 1950. The sociology of georg simmel. Vol. 92892. Simon and Schuster.
[48]
Tom AB Snijders. 2001. The statistical evaluation of social network dynamics. Sociological methodology 31, 1 (2001), 361–395.
[49]
Tom AB Snijders, Gerhard G Van de Bunt, and Christian EG Steglich. 2010. Introduction to stochastic actor-based models for network dynamics. Social networks 32, 1 (2010), 44–60.
[50]
Rakshit Trivedi, Mehrdad Farajtabar, Prasenjeet Biswal, and Hongyuan Zha. 2019. Dyrep: Learning representations over dynamic graphs. In ICLR.
[51]
Nate Veldt, Austin R Benson, and Jon Kleinberg. 2020. Minimizing Localized Ratio Cut Objectives in Hypergraphs. In KDD.
[52]
Yanbang Wang, Yen-Yu Chang, Yunyu Liu, Jure Leskovec, and Pan Li. 2021. Inductive Representation Learning in Temporal Graphs via Casual Anonymous Walk. In ICLR.
[53]
Da Xu, Chuanwei Ruan, Evren Korpeoglu, Sushant Kumar, and Kannan Achan. 2019. Self-attention with functional time representation learning. In NeurIPS.
[54]
Da Xu, Chuanwei Ruan, Evren Korpeoglu, Sushant Kumar, and Kannan Achan. 2020. Inductive Representation Learning on Temporal Graphs. In ICLR.
[55]
Naganand Yadati, Vikram Nitin, Madhav Nimishakavi, Prateek Yadav, Anand Louis, and Partha Talukdar. 2020. NHP: Neural Hypergraph Link Prediction. In KDD.
[56]
Hao Yin, Austin R Benson, Jure Leskovec, and David F Gleich. 2017. Local higher-order graph clustering. In KDD.
[57]
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 Web Conference.
[58]
Muhan Zhang and Yixin Chen. 2018. Link prediction based on graph neural networks. In NeurIPS.
[59]
Muhan Zhang, Zhicheng Cui, Shali Jiang, and Yixin Chen. 2018. Beyond link prediction: Predicting hyperlinks in adjacency space. In AAAI.
[60]
Muhan Zhang, Pan Li, Yinglong Xia, Kai Wang, and Long Jin. 2021. Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning. Advances in Neural Information Processing Systems 34 (2021).
[61]
Ruochi Zhang, Yuesong Zou, and Jian Ma. 2019. Hyper-SAGNN: a self-attention based graph neural network for hypergraphs. In ICLR.
[62]
Linhong Zhu, Dong Guo, Junming Yin, Greg Ver Steeg, and Aram Galstyan. 2016. Scalable temporal latent space inference for link prediction in dynamic social networks. IEEE Transactions on Knowledge and Data Engineering 28, 10(2016).

Cited By

View all
  • (2024)Benchtemp: A General Benchmark for Evaluating Temporal Graph Neural Networks2024 IEEE 40th International Conference on Data Engineering (ICDE)10.1109/ICDE60146.2024.00310(4044-4057)Online publication date: 13-May-2024
  • (2024)Correlation-enhanced Dynamic Graph Learning for Temporal Link Prediction2024 IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS)10.1109/EAIS58494.2024.10570036(1-7)Online publication date: 23-May-2024
  • (2024)Higher-order neurodynamical equation for simplex predictionNeural Networks10.1016/j.neunet.2024.106185173(106185)Online publication date: May-2024
  • Show More Cited By

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
WWW '22: Proceedings of the ACM Web Conference 2022
April 2022
3764 pages
ISBN:9781450390965
DOI:10.1145/3485447
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: 25 April 2022

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. Graph Representation Learning
  2. Hypergraph
  3. Network Science

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Funding Sources

Conference

WWW '22
Sponsor:
WWW '22: The ACM Web Conference 2022
April 25 - 29, 2022
Virtual Event, Lyon, France

Acceptance Rates

Overall Acceptance Rate 1,899 of 8,196 submissions, 23%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)414
  • Downloads (Last 6 weeks)49
Reflects downloads up to 30 Aug 2024

Other Metrics

Citations

Cited By

View all
  • (2024)Benchtemp: A General Benchmark for Evaluating Temporal Graph Neural Networks2024 IEEE 40th International Conference on Data Engineering (ICDE)10.1109/ICDE60146.2024.00310(4044-4057)Online publication date: 13-May-2024
  • (2024)Correlation-enhanced Dynamic Graph Learning for Temporal Link Prediction2024 IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS)10.1109/EAIS58494.2024.10570036(1-7)Online publication date: 23-May-2024
  • (2024)Higher-order neurodynamical equation for simplex predictionNeural Networks10.1016/j.neunet.2024.106185173(106185)Online publication date: May-2024
  • (2024)Ambiguities in neural-network-based hyperedge predictionJournal of Applied and Computational Topology10.1007/s41468-024-00172-xOnline publication date: 7-May-2024
  • (2024)Higher-Order Temporal Network PredictionComplex Networks & Their Applications XII10.1007/978-3-031-53503-1_38(461-472)Online publication date: 29-Feb-2024
  • (2023)CAT-WALKProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3667538(32636-32671)Online publication date: 10-Dec-2023
  • (2023)SUREL+: Moving from Walks to Sets for Scalable Subgraph-Based Graph Representation LearningProceedings of the VLDB Endowment10.14778/3611479.361149916:11(2939-2948)Online publication date: 1-Jul-2023
  • (2023)Expressive and Efficient Representation Learning for Ranking Links in Temporal GraphsProceedings of the ACM Web Conference 202310.1145/3543507.3583476(567-577)Online publication date: 30-Apr-2023
  • (2023)Exhaustive Evaluation of Dynamic Link Prediction2023 IEEE International Conference on Data Mining Workshops (ICDMW)10.1109/ICDMW60847.2023.00147(1121-1130)Online publication date: 4-Dec-2023
  • (2023)Temporal Graph Representation Learning with Adaptive Augmentation ContrastiveMachine Learning and Knowledge Discovery in Databases: Research Track10.1007/978-3-031-43415-0_40(683-699)Online publication date: 18-Sep-2023
  • Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Get Access

Login options

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media