Abstract
Information diffusion prediction, as a fundamental task in social network analysis, aims to identify potential users who are likely to participate in an information diffusion process. Most existing works learn user representations based on the collected social network data and then complete downstream prediction tasks. However, due to data privacy protection and low data quality, these methods are always limited by weak information issues of the social network data. For example, incomplete network structure, sparse labels, and insufficient features severely obstruct user representation learning. To mitigate these issues, we design an effective two-stage method MGCL. In the first stage, an enhanced representation is learned for every user even though the social network is with weak information. A multiplex heterogeneous network is adaptively constructed to enrich social network information. To facilitate user representation learning under sparse labels and insufficient features, we further propose self-supervised training specifically tailored for social networks with weak information. In the second stage, the cascade representations are learned using the multi-head self-attention network for information diffusion prediction. Extensive experiments on four real-world datasets validate that MGCL always outperforms state-of-the-art methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Li, J., Yang, Y., Hu, Q., Wang, X., Gao, H.: Public opinion field effect fusion in representation learning for trending topics diffusion. In: NeurIPS (2023)
Sun L., Rao, Y., Wu, L., Zhang, X., Lan, Y., Nazir, A.: Fighting false information from propagation process: a survey. In: ACM Computing Surveys, vol. 55(10), pp. 1–38 (2023)
Chen, J., Hoops, S., Marathe, A., Mortveit, H., Lewis, B., Venkatramanan, S., et al.: Effective social network-based allocation of COVID-19 vaccines. In: KDD, pp. 1675–1683 (2022)
Broekaert, J. B., La Torre, D., Hafiz, F.: Competing control scenarios in probabilistic SIR epidemics on social-contact networks. In: ArXiv./abs/2108.13714 (2021)
Cheng, J., Adamic, L., Dow, P., Kleinberg, J. M., Leskovec, J.: Can cascades be predicted? In: WWW, pp. 925–936 (2014)
Gao, S., Ma, J., Chen, Z.: Effective and effortless features for popularity prediction in microblogging network. In: WWW, pp. 269–270 (2014)
Wang, J., Zheng, V. W., Liu, Z., Chang, K. C.: Topological recurrent neural network for diffusion prediction. In: ICDM, pp. 475–484 (2017)
Yang, C., Sun, M., Liu, H., Han, S., Liu, Z., Luan, H.: Neural diffusion model for microscopic cascade study. TKDE 33(3), 1128–1139 (2021)
Wang, Z., Chen, C., Li, W.: A sequential neural information diffusion model with structure attention. In: CIKM, pp. 1795–1798 (2018)
Sankar, A., Zhang, X., Krishnan, A., Han, J.: Inf-VAE: a variational autoencoder framework to integrate homophily and influence in diffusion prediction. In: WSDM, pp. 510–518 (2020)
Yang, C., Tang, J., Sun, M., Cui, G., Liu, Z.: Multi-scale information diffusion prediction with reinforced recurrent networks. In: IJCAI, pp. 4033–4039 (2019)
Yuan, C., Li, J., Zhou, W., Lu, Y., Zhang, X., Hu, S.: DyHGCN: a dynamic heterogeneous graph convolutional network to learn users’ dynamic preferences for information diffusion prediction. In: ECML/PKDD, pp. 347–363 (2020)
Sun, L., Rao, Y., Zhang, X., Lan, Y., Yu, S.: MS-HGAT: memory-enhanced sequential hypergraph attention network for information diffusion prediction. In: AAAI, pp. 4156–4164 (2022)
Liu, Y., Ding, K., Wang J., Lee, V., Liu, H., Pan, S.: Learning strong graph neural networks with weak information. In: KDD, pp. 1559–1571 (2023)
Yu, P., Fu, C., Yu, Y., Huang, C., Zhao, Z., Dong, J.: Multiplex heterogeneous graph convolutional network. In: KDD, pp. 2377–2387 (2022)
Hamilton, W. L., Ying, R., Leskovec, J.: Inductive representation learning on large graphs. In: NeurPIS (2017)
Vaswani, A., et al.: Attention is all you need. In: NeurIPS, pp. 5998–6008 (2017)
Wang, Z., Zhu, Y., Wang, C., Ma, W., Li, B., Yu, J.: Adaptive graph representation learning for next POI recommendation. In: WWW, pp. 393–402 (2023)
Zhang, H., Yang, Y., Wang, X., Gao, H., Hu, Q.: MLI: A multi-level inference mechanism for user attributes in social networks. In: TOIS, vol. 41(2), 1–30 (2022)
Wang, H., Yang, C., Shi, C.: Neural information diffusion prediction with topic-aware attention network. In: CIKM, pp. 1899–1908 (2021)
Velickovic, P., Fedus, W., Hamilton, W.L., Li‘o, P., Bengio, Y., Hjelm, R.D.: Deep graph infomax. In: ICLR (Poster) (2019)
Hjelm, R.D., et al.: Learning deep representations by mutual information estimation and maximization. In: arXiv preprint arXiv:1808.06670 (2018)
You, Y., Chen, T., Sui, Y., Chen, T., Wang, Z., Shen, Y.: Graph contrastive learning with augmentations. In: NeurIPS, pp. 5812–5823 (2020)
Zhu, Y., Xu, Y., Yu, F., Liu, Q., Wu, S., Wang, L.: Graph contrastive learning with adaptive augmentation. In: WWW, pp. 2069–2080 (2021)
Hassani, K., Khasahmadi, A. H.: Contrastive multi-view representation learning on graphs. In: ICML, pp. 4116–4126 (2022)
An, W., Tian, F., Chen, P., Tang, S., Zheng, Q., Wang, Q.: Fine-grained category discovery under coarse-grained supervision with hierarchical weighted self-contrastive learning. In: EMNLP, pp. 1314–1323 (2022)
Hodas, N.O., Lerman, K.: The simple rules of social contagion. In: Scientific Reports, pp. 1–7 (2014)
Zhong, E., Fan, W., Wang, J., Xiao, L., Li, Y.: ComSoc: adaptive transfer of user behaviors over composite social network. In: KDD, pp. 696–704 (2012)
Acknowledgments
This work was supported by the State Key Laboratory of Communication Content Cognition Funded Project No. A32003, National Natural Science Foundation of China No. U22A2025 and No. 61972275.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Feng, Z. et al. (2024). Multi-level Contrastive Learning on Weak Social Networks for Information Diffusion Prediction. In: Onizuka, M., et al. Database Systems for Advanced Applications. DASFAA 2024. Lecture Notes in Computer Science, vol 14855. Springer, Singapore. https://doi.org/10.1007/978-981-97-5572-1_6
Download citation
DOI: https://doi.org/10.1007/978-981-97-5572-1_6
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-5571-4
Online ISBN: 978-981-97-5572-1
eBook Packages: Computer ScienceComputer Science (R0)