skip to main content
10.1145/3665348.3665371acmotherconferencesArticle/Chapter ViewAbstractPublication PagesgaiisConference Proceedingsconference-collections
research-article

Cluster information-driven graph convolutional networks for higher-order patterns prediction

Published: 03 July 2024 Publication History

Abstract

Through the mechanism of propagating and aggregating information, graph neural networks have achieved impressive results in link prediction tasks. However, the higher-order patterns (higher-order links) prediction task is still challenging. The conventional idea directly expands existing methods used in pairwise relationship prediction. Information propagation is limited to local neighborhoods and the evaluation basis uses only the similarity between pairs of nodes. These methods fail to consider the underlying driving factors of higher-order formation processes. Therefore, a key strategy is introducing a driving factor that helps information propagation beyond the local scope and provides a global comparable criterion between multiple nodes. Cluster structure is one crucial driving factor observed in networks, where nodes within the same cluster exhibit similar behaviors and tend to form higher-order patterns. To this end, we use Clustering Information as a Driving factor for graph structure adjustments in Graph Convolutional Network (CIDGCN). CIDGCN uses clustering information to facilitate the prediction of higher-order patterns. It also extends the propagation of node information to the cluster level for Graph Convolutional Network to perform message-passing. Finally, we obtain more reliable features for higher-order patterns. CIDGCN is experimentally compared to four higher-order benchmarks, revealing its superiority in accurately predicting higher-order patterns.

References

[1]
Zhang Z, Cui P, Zhu W. Deep learning on graphs: A survey[J]. IEEE Transactions on Knowledge and Data Engineering, 2020, 34(1): 249-270.
[2]
Yu J, Yin H, Xia X, Self-supervised learning for recommender systems: A survey[J]. IEEE Transactions on Knowledge and Data Engineering, 2023.
[3]
Li P, Milenkovic O. Inhomogeneous hypergraph clustering with applications[J]. Advances in neural information processing systems, 2017, 30.
[4]
Yang R, Sala F, Bogdan P. Efficient representation learning for higher-order data with simplicial complexes[C]//Learning on Graphs Conference. PMLR, 2022: 13: 1-13: 21.
[5]
Nie Y, Li W, Pan L, Markovian approach to tackle competing pathogens in simplicial complex[J]. Applied Mathematics and Computation, 2022, 417: 126773.
[6]
Ju W, Fang Z, Gu Y, A comprehensive survey on deep graph representation learning[J]. Neural Networks, 2024: 106207.
[7]
Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks[J]. arXiv preprint arXiv: 1609.02907, 2016.
[8]
Zhang W, Sheng Z, Yang M, NAFS: a simple yet tough-to-beat baseline for graph representation learning[C]//International Conference on Machine Learning. PMLR, 2022: 26467-26483.
[9]
Tolstikhin I O, Houlsby N, Kolesnikov A, Mlp-mixer: An all-mlp architecture for vision[J]. Advances in neural information processing systems, 2021, 34: 24261-24272.
[10]
Grover A, Leskovec J. node2vec: Scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining. 2016: 855-864.
[11]
Kipf T N, Welling M. Variational graph auto-encoders[J]. arXiv preprint arXiv: 1611.07308, 2016.
[12]
Antelmi A, Cordasco G, Polato M, A survey on hypergraph representation learning[J]. ACM Computing Surveys, 2023, 56(1): 1-38.
[13]
Antelmi A, Cordasco G, Polato M, A survey on hypergraph representation learning[J]. ACM Computing Surveys, 2023, 56(1): 1-38.
[14]
Sun H, Radicchi F, Kurths J, The dynamic nature of percolation on networks with triadic interactions[J]. Nature Communications, 2023, 14(1): 1308.
[15]
Cui P, Wang X, Pei J, A survey on network embedding[J]. IEEE transactions on knowledge and data engineering, 2018, 31(5): 833-852.
[16]
Xie J, Girshick R, Farhadi A. Unsupervised deep embedding for clustering analysis[C]//International conference on machine learning. PMLR, 2016: 478-487.
[17]
Yang B, Fu X, Sidiropoulos N D, Towards k-means-friendly spaces: Simultaneous deep learning and clustering[C]//international conference on machine learning. PMLR, 2017: 3861-3870.
[18]
Benson A R, Abebe R, Schaub M T, Simplicial closure and higher-order link prediction[J]. Proceedings of the National Academy of Sciences, 2018, 115(48): E11221-E11230.
[19]
Zhang Z, Sabuncu M. Generalized cross entropy loss for training deep neural networks with noisy labels[J]. Advances in neural information processing systems, 2018, 31.

Index Terms

  1. Cluster information-driven graph convolutional networks for higher-order patterns prediction

      Recommendations

      Comments

      Information & Contributors

      Information

      Published In

      cover image ACM Other conferences
      GAIIS '24: Proceedings of the 2024 International Conference on Generative Artificial Intelligence and Information Security
      May 2024
      439 pages
      ISBN:9798400709562
      DOI:10.1145/3665348
      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 the author(s) 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].

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      Published: 03 July 2024

      Permissions

      Request permissions for this article.

      Check for updates

      Qualifiers

      • Research-article
      • Research
      • Refereed limited

      Conference

      GAIIS 2024

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • 0
        Total Citations
      • 21
        Total Downloads
      • Downloads (Last 12 months)21
      • Downloads (Last 6 weeks)4
      Reflects downloads up to 17 Feb 2025

      Other Metrics

      Citations

      View Options

      Login 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

      Figures

      Tables

      Media

      Share

      Share

      Share this Publication link

      Share on social media