Skip to main content

Sparse relation prediction based on hypergraph neural networks in online social networks

Abstract

In recent years, online social networks (OSNs) have thoroughly penetrated people’s lives. Since information always flows along with various online relations in OSNs, analysing these relations becomes one of the most fundamental problems in various applications. Unfortunately, limited by the privacy concerns, data availability and the pow-law distributions of most OSNs, we can not observe enough relation links all the time, which is difficult to improve downstream tasks. To address this problem, many studies try to predict potential relations in online social networks via existing pair-wise links. However, when the observable pair-wise links are extremely sparse, most of them fail to learn the smoothness on the networks and make their proposed methods brittle. In light of this, we go beyond pair-wise relations and leverage hypergraphs to learn higher relations in the graphs. A hypergraph allows one hyperedge to connect multiple nodes, which is perfect to include more potential pair-wise links and can guarantee smooth node embeddings for better link prediction performance. In this paper, we aim at predicting potential links in sparsely observed networks. To achieve this goal, we first start from some blurry hyperedges and then proposed a novel hyperedge shrinking method to make the learned hyperedges more hierarchical. This method can learn hypergraph structure automatically from the given sparsely observed links and rely less on manual design. Following this, we further propose a novel hypergraph-based graph neural network to learn potential links in the graph. To address semantic fusion in the heterogeneous networks, we put forward multi-level reconstruction methods to preserve both specific semantics denoted by meta-paths, and high-level semantics denoted by hypergraphs. We compare our method with four state-of-the-art baselines. Extensive evaluations demonstrate that our method can achieve the best linking prediction results, especially when the networks are sparse.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

References

  1. 1.

    Ahmed, A., Shervashidze, N., Narayanamurthy, S., Josifovski, V., Smola, A.J.: Distributed Large-Scale Natural Graph Factorization. In: The Web Conference (WWW) (2013)

  2. 2.

    Angluin, D., Chen, J.: Learning a hidden hypergraph. J. Mach. Learn. Res. 7(Oct), 2215–2236 (2006)

    MathSciNet  MATH  Google Scholar 

  3. 3.

    Benson, A.R., Abebe, R., Schaub, M.T., Jadbabaie, A., Kleinberg, J.: Simplicial closure and higher-order link prediction. Proc. Natl. Acad. Sci. 115(48), E11221–E11230 (2018)

    Article  Google Scholar 

  4. 4.

    Blondel, V.D., Guillaume, J.L., Lambiotte, R., Lefebvre, E.: Fast unfolding of communities in large networks Journal of statistical mechanics: theory and experiment (2008)

  5. 5.

    Cai, L., Ji, S.: A multi-scale approach for graph link prediction. In: 34Th AAAI Conference on Artificial Intelligence, pp 3308–3315. AAAI (2020)

  6. 6.

    Cai, T., Li, J., Mian, A.S., Sellis, T., Yu, J.X., et al.: Target-aware holistic influence maximization in spatial social networks. IEEE Transactions on Knowledge and Data Engineering (2020)

  7. 7.

    Cen, Y., Zou, X., Zhang, J., Yang, H., Zhou, J., Tang, J.: Representation learning for attributed multiplex heterogeneous network. In: 25Th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’19), pp. 1358–1368 (2019)

  8. 8.

    Chen, H., Yin, H., Sun, X., Chen, T., Gabrys, B., Musial, K.: Multi-level graph convolutional networks for cross-platform anchor link prediction. In: 26Th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’20) (2020)

  9. 9.

    Chen, H., Yin, H., Wang, W., Wang, H., Nguyen, Q.V.H., Li, X.: PME: Projected metric embedding on heterogeneous networks for link prediction. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1177–1186. ACM (2018)

  10. 10.

    Chen, T., Yin, H., Chen, H., Yan, R., Nguyen, Q.V.H., Li, X.: Air: attentional intention-aware recommender systems. In: 35Th IEEE International Conference on Data Engineering (ICDE), pp. 304–315 (2019)

  11. 11.

    Cheng, A., Zhou, C., Yang, H., Wu, J., Li, L., Tan, J., Guo, L.: Deep active learning for anchor user prediction. The Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI) (2019)

  12. 12.

    Chu, Y., Feng, C., Guo, C.: Social-Guided Representation Learning for Images via Deep Heterogeneous Hypergraph Embedding. In: 2018 IEEE International Conference on Multimedia and Expo (ICME), pp. 1–6. IEEE (2018)

  13. 13.

    Das, M., Dhami, D.S., Kunapuli, G., Kersting, K., Natarajan, S.: Fast relational probabilistic inference and learning: approximate counting via hypergraphs. In: AAAI Conference on Artificial Intelligence, vol. 33, pp. 7816–7824 (2019)

  14. 14.

    Dong, Y., Chawla, N.V., Swami, A.: Metapath2vec: Scalable representation learning for heterogeneous networks. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 135–144 (2017)

  15. 15.

    Feng, Y., You, H., Zhang, Z., Ji, R., Gao, Y.: Hypergraph neural networks. In: AAAI Conference on Artificial Intelligence, vol. 33, pp. 3558–3565 (2019)

  16. 16.

    Fu, X., Zhang, J., Meng, Z., King, I.: MAGNN: Metapath aggregated graph neural network for heterogeneous graph embedding. In: The Web Conference (WWW), pp. 2331–2341 (2020)

  17. 17.

    Grover, A., Leskovec, J: Node2vec: Scalable feature learning for networks. In: 22Th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’16), pp. 855–864 (2016)

  18. 18.

    Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: The 31St Annual Conference on Neural Information Processing Systems (NeurIPS), pp. 1024–1034 (2017)

  19. 19.

    Hao, X., Lian, T., Wang, L.: Dynamic link prediction by integrating node vector evolution and local neighborhood representation. In: The 43Rd ACM SIGIR Conference (SIGIR), pp. 1717–1720 (2020)

  20. 20.

    Hao, Y., Cao, X., Fang, Y., Xie, X., Wang, S.: Inductive link prediction for nodes having only attribute information. In: The 29Th International Joint Conference on Artificial Intelligence (IJCAI), pp. 1209–1215 (2020)

  21. 21.

    He, X., Deng, K., Wang, X., Li, Y., Zhang, Y., Wang, M.: LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation. In: The 43Rd ACM SIGIR Conference (SIGIR), pp. 639–648 (2020)

  22. 22.

    He, Y., Song, Y., Li, J., Ji, C., Peng, J., Peng, H.: Hetespaceywalk: a Heterogeneous spacey random walk for heterogeneous information network embedding. In: The 28Th ACM International Conference on Information and Knowledge Management (CIKM), pp. 639–648 (2019)

  23. 23.

    Hu, B., Fang, Y., Shi, C.: Adversarial learning on heterogeneous information networks. In: 25Th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’19), pp. 120–129 (2019)

  24. 24.

    Hu, B., Zhang, Z., Shi, C., Zhou, J., Li, X., Qi, Y.: Cash-out user detection based on attributed heterogeneous information network with a hierarchical attention mechanism. In: AAAI Conference on Artificial Intelligence, vol. 33, pp. 946–953 (2019)

  25. 25.

    Jiang, J., Wei, Y., Feng, Y., Cao, J., Gao, Y.: Dynamic hypergraph neural networks. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI), pp. 2635–2641 (2019)

  26. 26.

    Jin, T., Cao, L., Zhang, B., Sun, X., Deng, C., Ji, R.: Hypergraph induced convolutional manifold networks. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI), pp. 2670–2676 (2019)

  27. 27.

    Joshi, U., Urbani, J.: Searching for Embeddings in a Haystack: Link Prediction on Knowledge Graphs with Subgraph Pruning. In: The Web Conference (WWW), pp. 2817–2823 (2020)

  28. 28.

    Li, X., Shang, Y., Cao, Y., Li, Y., Tan, J., Liu, Y.: Type-Aware Anchor Link Prediction across Heterogeneous Networks Based on Graph Attention Network. In: AAAI Conference on Artificial Intelligence, vol. 34, pp. 147–155 (2020)

  29. 29.

    Ma, H., Zhang, D., Zhao, W., Wang, Y., Shi, Z.: Leveraging hypergraph random walk tag expansion and user social relation for microblog recommendation. In: 2018 IEEE International Conference on Data Mining (ICDM), pp. 1158–1163. IEEE (2018)

  30. 30.

    McCallum, A.K., Nigam, K., Rennie, J., Seymore, K.: Automating the construction of internet portals with machine learning. Inf. Retr. 3(2), 127–163 (2000)

    Article  Google Scholar 

  31. 31.

    Ng, A.Y., Jordan, M.I., Weiss, Y.: On Spectral Clustering: Analysis and an Algorithm. In: The 16Th Annual Conference on Neural Information Processing Systems (NeurIPS) (2002)

  32. 32.

    Niepert, M., Ahmed, M., Kutzkov, K.: Learning convolutional neural networks for graphs. In: The 33Rd International Conference on Machine Learning (ICML), pp. 2014–2023 (2016)

  33. 33.

    Ostapuk, N., Yang, J., Cudré-Mauroux, P.: Activelink: Deep active learning for link prediction in knowledge graphs. In: The Web Conference (WWW), pp. 1398–1408 (2019)

  34. 34.

    Perozzi, B., Al-Rfou, R., Skiena, S.: Deepwalk: Online learning of social representations. In: 20Th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’14), pp. 701–710 (2014)

  35. 35.

    Qu, L., Zhu, H., Duan, Q., Shi, Y.: Continuous-time link prediction via temporal dependent graph neural network. In: The Web Conference (WWW), pp. 3026–3032 (2020)

  36. 36.

    Rosso, P., Yang, D., Cudré-Mauroux, P.: Beyond triplets: hyper-relational knowledge graph embedding for link prediction. In: The Web Conference (WWW), pp. 1885–1896 (2020)

  37. 37.

    Shao, J., Zhang, Z., Yu, Z., Wang, J., Zhao, Y., Yang, Q.: Community detection and link prediction via cluster-driven low-rank matrix completion. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI), pp. 3382–3388 (2019)

  38. 38.

    Singh, R., Xu, J., Berger, B.: Global alignment of multiple protein interaction networks with application to functional orthology detection. Proceedings of the National Academy of Sciences (2008)

  39. 39.

    Sun, X., Yin, H., Liu, B., Chen, H., Cao, J., Shao, Y., Hung, N.Q.V.: Heterogeneous hypergraph embedding for graph classification. In: The International Conference on Web Search and Data Mining (WSDM) (2019)

  40. 40.

    Tang, J., Qu, M., Mei, Q.: PTE: Predictive text embedding through large-scale heterogeneous text networks. In: 21St ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’15) (2015)

  41. 41.

    Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., Mei, Q.: Line: large-scale information network embedding. In: The Web Conference (WWW) (2015)

  42. 42.

    Thida, M., Eng, H.L., Remagnino, P.: Laplacian eigenmap with temporal constraints for local abnormality detection in crowded scenes. IEEE Transactions on Cybernetics (2013)

  43. 43.

    Trung, H.T., Toan, N.T., Van Vinh, T., Dat, H.T., Thang, D.C., Hung, N.Q.V., Sattar, A.: A comparative study on network alignment techniques. Expert Systems with Applications (2020)

  44. 44.

    Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks 10th. International Conference on Learning Representations (ICLR) (2018)

  45. 45.

    Wang, H., Zhang, F., Hou, M., Xie, X., Guo, M., Liu, Q.: SHINE: signed heterogeneous information network embedding for sentiment link prediction. In: The International Conference on Web Search and Data Mining (WSDM), pp. 592–600 (2018)

  46. 46.

    Wang, W., Yin, H., Du, X., Hua, W., Li, Y., Nguyen, Q.V.H.: Online user representation learning across heterogeneous social networks. In: The 42Nd ACM SIGIR Conference (SIGIR), pp. 545–554 (2019)

  47. 47.

    Wang, X., Ji, H., Shi, C., Wang, B., Ye, Y., Cui, P., Yu, P.S.: Heterogeneous graph attention network. In: The Web Conference (WWW), pp. 2022–2032 (2019)

  48. 48.

    Wang, X., Lu, Y., Shi, C., Wang, R., Cui, P., Mou, S.: Dynamic heterogeneous information network embedding with meta-path based proximity. IEEE Transactions on Knowledge and Data Engineering (2020)

  49. 49.

    Wang, X., Zhang, Y., Shi, C.: Hyperbolic heterogeneous information network embedding. In: AAAI Conference on Artificial Intelligence, vol. 33, pp. 5337–5344 (2019)

  50. 50.

    Wang, Z., Ren, Z., He, C., Zhang, P., Hu, Y.: Robust embedding with multi-level structures for link prediction. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI), pp. 5240–5246 (2019)

  51. 51.

    Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., Philip, S.Y.: A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems (2020)

  52. 52.

    Xie, X., Qin, X.: Dynamic feature selection algorithm based on minimum vertex cover of hypergraph. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining, pp. 40–51. Springer (2018)

  53. 53.

    Yang, D., Qu, B., Yang, J., Cudre-Mauroux, P.: Revisiting user mobility and social relationships in LBSNs: A hypergraph embedding approach. In: The Web Conference (WWW), pp. 2147–2157 (2019)

  54. 54.

    Yoon, S.E., Song, H., Shin, K., Yi, Y.: How much and when do we need higher-order informationin hypergraphs? a case study on hyperedge prediction. In: The Web Conference (WWW), pp. 2627–2633 (2020)

  55. 55.

    Yuanfu, L., Chuan Shi, L.H.Z.L.: Relation structure-aware heterogeneous information network embedding. In: AAAI Conference on Artificial Intelligence (2019)

  56. 56.

    Zhang, M., Cui, Z., Jiang, S., Chen, Y.: Beyond link prediction: predicting hyperlinks in adjacency space. In: 32Nd AAAI Conference on Artificial Intelligence (2018)

  57. 57.

    Zhang, R., Zou, Y., Ma, J.: Hyper-SAGNN: a self-attention based graph neural network for hypergraphs. In: 8Th International Conference on Learning Representations (ICLR) (2020)

  58. 58.

    Zhang, Z., Lin, H., Gao, Y.: Dynamic hypergraph structure learning. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI), pp. 3162–3169 (2018)

  59. 59.

    Zhao, S., Ding, G., Han, J., Gao, Y.: Personality-aware personalized emotion recognition from physiological signals. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI), pp. 1660–1667 (2018)

  60. 60.

    Zheng, X., Luo, Y., Sun, L., Ding, X., Zhang, J.: A novel social network hybrid recommender system based on hypergraph topologic structure. World Wide Web J. 21(4), 985–1013 (2018)

    Article  Google Scholar 

  61. 61.

    Zhou, D., Huang, J., Schölkopf, B.: Learning with Hypergraphs: Clustering, classification, and embedding. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 1601–1608 (2007)

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Xiangguo Sun.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This article belongs to the Topical Collection: Special Issue on Decision Making in Heterogeneous Network Data Scenarios and Applications

Guest Editors: Jianxin Li, Chengfei Liu, Ziyu Guan, and Yinghui Wu

Xiangguo Sun is the corresponding author, and have contributed equally with the first author.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Guan, Y., Sun, X. & Sun, Y. Sparse relation prediction based on hypergraph neural networks in online social networks. World Wide Web (2021). https://doi.org/10.1007/s11280-021-00936-w

Download citation

Keywords

  • Hypergraph neural network
  • Link prediction
  • Heterogeneous networks