ABSTRACT
Link prediction, which centers on whether or not a pair of nodes is likely to be connected, is a fundamental problem in complex network analysis. Network-embedding-based link prediction has shown strong performance and robustness in previous studies on complex networks, recommendation systems, and knowledge graphs. This approach has certain drawbacks, however; namely, the hierarchical structure of a subgraph is ignored and the importance of different nodes is not distinguished. In this study, we established the Subgraph Hierarchy Feature Fusion (SHFF) model for link prediction. To probe the existence of links between node pairs, the SHFF first extracts a subgraph around the two nodes and learns a function to map the subgraph to a vector for subsequent classification. This reveals any link between the two target nodes. The SHFF learns a function to obtain a representation of the extracted subgraph by hierarchically aggregating the features of nodes in that subgraph, which is accomplished by grouping nodes with similar structures and assigning different importance to the nodes during the feature fusion process. We compared the proposed model against other state-of-the-art link-prediction methods on a wide range of data sets to find that it consistently outperforms them.
Supplemental Material
- Ackland, R., et al. Mapping the us political blogosphere: Are conservative bloggers more prominent? In BlogTalk Downunder 2005 Conference, Sydney (2005).Google Scholar
- Adamic, L. A., and Adar, E. Friends and neighbors on the web. Social networks 25, 3 (2003), 211--230.Google Scholar
- Aslam, J. A., Yilmaz, E., and Pavlu, V. The maximum entropy method for analyzing retrieval measures. In Proceedings of the 28th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (New York, NY, USA, 2005), SIGIR '05, Association for Computing Machinery, pp. 27--34.Google Scholar
- Barabási, A.-L., and Albert, R. Emergence of scaling in random networks. science 286, 5439 (1999), 509--512.Google Scholar
- Barbieri, N., Bonchi, F., and Manco, G. Who to follow and why: link prediction with explanations. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2014), pp. 1266--1275.Google ScholarDigital Library
- Brin, S., and Page, L. The anatomy of a large-scale hypertextual web search engine. Computer Networks and ISDN System 30, 1--7 (1998), 107--117.Google ScholarDigital Library
- Cao, Z., Qin, T., Liu, T.-Y., Tsai, M.-F., and Li, H. Learning to rank: from pairwise approach to listwise approach. In Proceedings of the 24th International Conference on Machine Learning (2007), pp. 129--136.Google ScholarDigital Library
- Chen, H., Yin, H., Wang, W., Wang, H., Nguyen, Q. V. H., and Li, X. Pme: projected metric embedding on heterogeneous networks for link prediction. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2018), pp. 1177--1186.Google ScholarDigital Library
- Chowdhury, G. G. Introduction to modern information retrieval. Facet publishing, 2010.Google ScholarDigital Library
- Dai, H., Dai, B., and Song, L. Discriminative embeddings of latent variable models for structured data. In Proceedings of the 33rd International Conference on Machine Learning (2016), pp. 2702--2711.Google ScholarDigital Library
- Duvenaud, D. K., Maclaurin, D., Iparraguirre, J., Bombarell, R., Hirzel, T., Aspuru-Guzik, A., and Adams, R. P. Convolutional networks on graphs for learning molecular fingerprints. In Proceedings of the Advances in Neural Information Processing Systems (2015), pp. 2224--2232.Google Scholar
- Gilmer, J., Schoenholz, S. S., Riley, P. F., Vinyals, O., and Dahl, G. E. Neural message passing for quantum chemistry. In Proceedings of the 34th International Conference on Machine Learning-Volume 70 (2017), JMLR, pp. 1263--1272.Google ScholarDigital Library
- Grover, A., and Leskovec, J. node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2016), pp. 855--864.Google ScholarDigital Library
- Jeh, G., and Widom, J. Simrank: a measure of structural-context similarity. In Proceedings of the eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2002), pp. 538--543.Google ScholarDigital Library
- Katz, L. A new status index derived from sociometric analysis. Psychometrika 18, 1 (1953), 39--43.Google ScholarCross Ref
- Kossinets, G. Effects of missing data in social networks. Social networks 28, 3 (2006), 247--268.Google Scholar
- Lee, J., Lee, I., and Kang, J. Self-attention graph pooling. arXiv preprint arXiv:1904.08082 (2019).Google Scholar
- Liben-Nowell, D., and Kleinberg, J. The link-prediction problem for social networks. Journal of the American society for information science and technology 58, 7 (2007), 1019--1031.Google Scholar
- Lichtenwalter, R. N., Lussier, J. T., and Chawla, N. V. New perspectives and methods in link prediction. In Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2010), pp. 243--252.Google ScholarDigital Library
- Ma, Y., Wang, S., Aggarwal, C. C., and Tang, J. Graph convolutional networks with eigenpooling. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2019), pp. 723--731.Google ScholarDigital Library
- Negi, S., and Chaudhury, S. Link prediction in heterogeneous social networks. In Proceedings of the 25th ACM International on Conference on Information and Knowledge Management (2016), pp. 609--617.Google ScholarDigital Library
- Newman, M. Networks: An Introduction. Oxford University Press, 2010.Google ScholarCross Ref
- Newman, M. E. Clustering and preferential attachment in growing networks. Physical review E 64, 2 (2001), 025102.Google Scholar
- Newman, M. E. Finding community structure in networks using the eigenvectors of matrices. Physical review E 74, 3 (2006), 036104.Google Scholar
- Pal, S. K., and Mitra, S. Multilayer perceptron, fuzzy sets, and classification. IEEE Transactions on Neural Networks 3, 5 (1992), 683--697.Google ScholarDigital Library
- Perozzi, B., Al-Rfou, R., and Skiena, S. Deepwalk: Online learning of social representations. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2014), pp. 701--710.Google ScholarDigital Library
- Provost, F., and Fawcett, T. Analysis and visualization of classifier performance: Comparison under imprecise class and cost distributions. In Proceedings of the 3rd International Conference on Knowledge Discovery and Data Mining (1997), pp. 43--48.Google Scholar
- Ribeiro, L. F., Saverese, P. H., and Figueiredo, D. R. struc2vec: Learning node representations from structural identity. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2017), pp. 385--394.Google ScholarDigital Library
- Rossi, R. A., and Ahmed, N. K. The network data repository with interactive graph analytics and visualization. In Proceedings of the 29th AAAI Conference on Artificial Intelligence, pp. 4292--4293.Google Scholar
- Spring, N., Mahajan, R., and Wetherall, D. Measuring isp topologies with rocketfuel. ACM SIGCOMM Computer Communication Review 32, 4 (2002), 133--145.Google ScholarDigital Library
- Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., and Mei, Q. Line: Large-scale information network embedding. In Proceedings of the 24th International Conference on World Wide Web (2015), pp. 1067--1077.Google ScholarDigital Library
- Velivc ković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., and Bengio, Y. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017).Google Scholar
- Von Mering, C., Krause, R., Snel, B., Cornell, M., Oliver, S. G., Fields, S., and Bork, P. Comparative assessment of large-scale data sets of protein--protein interactions. Nature 417, 6887 (2002), 399--403.Google ScholarCross Ref
- Watts, D. J., and Strogatz, S. H. Collective dynamics of 'smallworld'networks. nature, 393 (6684): 440--442, 1998. Adaptive degree penalization for link prediction (2018).Google Scholar
- Wu, J., He, J., and Xu, J. Net: Degree-specific graph neural networks for node and graph classification. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2019), pp. 406--415.Google ScholarDigital Library
- Yu, H., Braun, P., Yildirim, M. A., Lemmens, I., Venkatesan, K., Sahalie, J., Hirozane-Kishikawa, T., Gebreab, F., Li, N., Simonis, N., et al. High-quality binary protein interaction map of the yeast interactome network. Science 322, 5898 (2008), 104--110.Google ScholarCross Ref
- Zhang, J., Yu, P. S., and Zhou, Z.-H. Meta-path based multi-network collective link prediction. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2014), pp. 1286--1295.Google ScholarDigital Library
- Zhang, M., and Chen, Y. Weisfeiler-lehman neural machine for link prediction. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2017), pp. 575--583.Google ScholarDigital Library
- Zhang, M., and Chen, Y. Link prediction based on graph neural networks. In Advances in Neural Information Processing Systems (2018), pp. 5165--5175.Google Scholar
- Zhang, M., Cui, Z., Neumann, M., and Chen, Y. An end-to-end deep learning architecture for graph classification. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence (2018), pp. 4438--4445.Google ScholarCross Ref
- Zhao, Z., Gao, B., Zheng, V. W., Cai, D., He, X., and Zhuang, Y. Link prediction via ranking metric dual-level attention network learning. In IJCAI (2017), pp. 3525--3531.Google ScholarDigital Library
- Zhou, F., Wu, B., Yang, Y., Trajcevski, G., Zhang, K., and Zhong, T. Vec2link: Unifying heterogeneous data for social link prediction. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management (2018), pp. 1843--1846.Google ScholarDigital Library
Index Terms
- Feature Fusion Based Subgraph Classification for Link Prediction
Recommendations
Attention Based Subgraph Classification for Link Prediction by Network Re-weighting
CIKM '21: Proceedings of the 30th ACM International Conference on Information & Knowledge ManagementSupervised link prediction aims at finding missing links in a network by learning directly from the data suitable criteria for classifying link types into existent or non-existent. Recently, along this line, subgraph-based methods learning a function ...
Link Prediction Based on the Sub-graphs Learning with Fused Features
Neural Information ProcessingAbstractAs one of the important research methods in the area of the knowledge graph completion, link prediction aims to capture the structural information or the attribute information of nodes in the network to predict the link probability between nodes, ...
Sampling Enclosing Subgraphs for Link Prediction
CIKM '22: Proceedings of the 31st ACM International Conference on Information & Knowledge ManagementLink prediction is a fundamental problem for graph-structured data (e.g., social networks, drug side-effect networks, etc.). Graph neural networks have offered robust solutions for this problem, specifically by learning the representation of the ...
Comments