Abstract
Link prediction is an important task for graph data. Methods based on graph neural networks achieve high accuracy by simultaneously modeling the node attributes and structure of the observed graph. However, these methods often get worse performance for low-degree nodes. After theoretical analysis, we find that current link prediction methods focus more on negative samples for low-degree nodes, which makes it hard to find potential neighbors for these nodes during inference. In order to improve the performance on low-degree nodes, we first design a node-wise score to quantify how seriously the training is biased to negative samples. Based on the score, we develop a reweighting method called harmonic weighting(HAW) to help the model preserve potential neighbors for low-degree nodes. Experimental results show that the model combined with HAW can achieve better performance on most datasets. By detailedly analyzing the performance on nodes with different degrees, we find that HAW can preserve more potential neighbors for low-degree nodes without reducing the performance of other nodes.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We use WP as a shorthand.
References
Brin, S., Page, L.: The anatomy of a large-scale hypertextual web search engine. Comput. Netw. ISDN Syst. 30(1–7), 107–117 (1998)
Cai, L., Ji, S.: A multi-scale approach for graph link prediction. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 3308–3315 (2020)
Cai, L., Li, J., Wang, J., Ji, S.: Line graph neural networks for link prediction. IEEE Trans. Pattern Anal. Mach. Intell. 44(9), 5103–5113 (2021)
Chen, X., et al.: Imagine by reasoning: a reasoning-based implicit semantic data augmentation for long-tailed classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 356–364 (2022)
Craven, M., et al.: Learning to extract symbolic knowledge from the world wide web. In: AAAI/IAAI, pp. 509–516 (1998)
Giles, C.L., Bollacker, K.D., Lawrence, S.: Citeseer: an automatic citation indexing system. In: Proceedings of the third ACM Conference on Digital Libraries, pp. 89–98 (1998)
Guo, Y., Gu, X., Wang, Z., Fan, H., Li, B., Wang, W.: Rcs: an attributed community search approach based on representation learning. In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2021)
Guo, Z., Wang, F., Yao, K., Liang, J., Wang, Z.: Multi-scale variational graph autoencoder for link prediction. In: Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining, pp. 334–342 (2022)
Jeh, G., Widom, J.: Simrank: a measure of structural-context similarity. In: Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 538–543 (2002)
Katz, L.: A new status index derived from sociometric analysis. Psychometrika 18(1), 39–43 (1953)
Kipf, T.N., Welling, M.: Variational graph auto-encoders. arXiv preprint arXiv:1611.07308 (2016)
Van der Maaten, L., Hinton, G.: Visualizing data using t-sne. J. Mach. Learn. Res. 9(11), 2579–2605 (2008)
McCallum, A.K., Nigam, K., Rennie, J., Seymore, K.: Automating the construction of internet portals with machine learning. Inf. Retr. 3, 127–163 (2000)
Namata, G., London, B., Getoor, L., Huang, B., Edu, U.: Query-driven active surveying for collective classification. In: 10th International Workshop on Mining and Learning with Graphs, vol. 8, pp. 1–8 (2012)
Pan, L., Shi, C., Dokmanić, I.: Neural link prediction with walk pooling. In: International Conference on Learning Representations (2022)
Pan, S., Hu, R., Long, G., Jiang, J., Yao, L., Zhang, C.: Adversarially regularized graph autoencoder for graph embedding. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, pp. 2609–2615 (2018)
Qian, M., Gu, X., Chu, L., Dai, F., Fan, H., Li, B.: Flexible order aware sequential recommendation. In: Proceedings of the 2022 International Conference on Multimedia Retrieval, pp. 109–117 (2022)
Stanfield, Z., Coşkun, M., Koyutürk, M.: Drug response prediction as a link prediction problem. Sci. Rep. 7(1), 1–13 (2017)
Wang, Z., Tan, Y., Zhang, M.: Graph-based recommendation on social networks. In: Proceedings of the 12th Asia-Pacific Web Conference, pp. 116–122. IEEE (2010)
Wu, X., Cheng, Q.: Stabilizing and enhancing link prediction through deepened graph auto-encoders. In: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence. vol. 2022, pp. 3587–3593. NIH Public Access (2022)
Yang, Y., Gu, X., Fan, H., Li, B., Wang, W.: Multi-granularity evolution network for dynamic link prediction. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining, pp. 393–405. Springer, Heidelberg (2022). https://doi.org/10.1007/978-3-031-05933-9_31
Zhang, M., Chen, Y.: Link prediction based on graph neural networks. Adv. Neural Inf. Process. Syst. 31, 5171–5181 (2018)
Zhou, T., Lü, L., Zhang, Y.C.: Predicting missing links via local information. Eur. Phys. J. B 71, 623–630 (2009)
Zitnik, M., Leskovec, J.: Predicting multicellular function through multi-layer tissue networks. Bioinformatics 33(14), i190–i198 (2017)
Acknowledgement
This work was supported in part by No.XDC02050200 and No.E110101114 program.
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
Li, Z., Zhou, Y., Fan, H., Gu, X., Li, B., Meng, D. (2024). Preserving Potential Neighbors for Low-Degree Nodes via Reweighting in Link Prediction. In: Luo, B., Cheng, L., Wu, ZG., Li, H., Li, C. (eds) Neural Information Processing. ICONIP 2023. Lecture Notes in Computer Science, vol 14448. Springer, Singapore. https://doi.org/10.1007/978-981-99-8082-6_43
Download citation
DOI: https://doi.org/10.1007/978-981-99-8082-6_43
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8081-9
Online ISBN: 978-981-99-8082-6
eBook Packages: Computer ScienceComputer Science (R0)