Abstract
Searching for a community containing a query node in an online social network enjoys wide applications like recommendation, team organization, etc. When applied to real-life networks, the existing approaches face two major limitations. First, they usually take two steps, i.e., crawling a large part of the network first and then finding the community next, but the entire network is usually too big and most of the data are not interesting to end users. Second, the existing methods utilize hand-crafted rules to measure community membership, while it is very difficult to define effective rules as the communities are flexible for different query nodes. This paper proposes an interactive community search method based on graph neural network (shortened by ICS-GNN\(^+\)) to locate the target community over a subgraph collected on the fly from an online network iteratively. In each iteration, we first build a candidate subgraph around the query node and labeled nodes. We then train a node classification model using GNN to determine whether every node belongs to the target community, which captures similarities between nodes by combining content and structural features seamlessly and flexibly under the guide of users’ labeling. Based on the probabilities inferred from the trained GNN, we introduce a k-sized Maximum-GNN-scores (shortened by kMG) community to describe the target community and design a method to locate the kMG community which will be evaluated by end users to acquire more feedback. Besides, various optimization strategies are proposed including an adaptive method to maintain the subgraph during iterations, combining ranking loss into the GNN model, generating node embedding enhanced by pseudo-labels from node clusters in the subgraph, and a greedy community searching method with benefit computed globally. We conduct the experiments on both offline and online real-life datasets, and demonstrate that ICS-GNN\(^+\) can produce effective communities with low overhead in communication, computation, and user labeling.
Similar content being viewed by others
References
Caron, M., Bojanowski, P., Joulin, A., Douze, M.: Deep clustering for unsupervised learning of visual features. In: European Conference on Computer Vision (2018)
Chen, Z., Li, L., Bruna, J.: Supervised community detection with line graph neural networks. In: ICLR (2019)
Cui, W., Xiao, Y., Wang, H., Lu, Y., Wang, W.: Online search of overlapping communities. In: SIGMOD, pp. 277–288 (2013)
Fang, Y., Cheng, R., Luo, S., Hu, J.: Effective community search for large attributed graphs. Proc. VLDB Endow. 9(12), 1233–1244 (2016)
Fang, Y., Huang, X., Qin, L., Zhang, Y., Zhang, W., Cheng, R., Lin, X.: A survey of community search over big graphs. VLDB J. 29(1), 353–392 (2020)
Fey, M., Lenssen, J.E.: Fast graph representation learning with pytorch geometric (2019). http://arxiv.org/pdf/1903.02428v3:PDF
Gao, J., Chen, J., Li, Z., Zhang, J.: ICS-GNN: lightweight interactive community search via graph neural network. Proc. VLDB Endow. 14(6), 1006–1018 (2021). https://doi.org/10.14778/3447689.3447704
Hamilton, W.L., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: NIPS, pp. 1024–1034 (2017)
Hamrick, J.B., Allen, K.R., Bapst, V., Zhu, T., McKee, K.R., Tenenbaum, J., Battaglia, P.W.: Relational inductive bias for physical construction in humans and machines. In: CogSci (2018)
He, X., Deng, K., Wang, X., Li, Y., Zhang, Y., Wang, M.: Lightgcn: simplifying and powering graph convolution network for recommendation. In: SIGIR, pp. 639–648 (2020)
Huang, X., Cheng, H., Qin, L., Tian, W., Yu, J.X.: Querying k-truss community in large and dynamic graphs. In: SIGMOD, pp. 1311–1322 (2014)
Huang, X., Lakshmanan, L.V.S.: Attribute-driven community search. Proc. VLDB Endow. 10(9), 949–960 (2017)
Karp, R.M.: Reducibility among combinatorial problems. In: Proceedings of a Symposium on the Complexity of Computer Computations, pp. 85–103 (1972)
Kendall, A., Gal, Y., Cipolla, R.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: CVPR (2018)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)
Learning, M., Science, C., Caruana, R.: Multitask Learning*. Betascript Publishing, Beau-Bassin (1997)
Li, B., Drozd, A., Guo, Y., Liu, T., Matsuoka, S., Du, X.: Scaling word2vec on big corpus. Data Sci. Eng. 2(4), 157–175 (2019)
Li, R., Qin, L., Yu, J.X., Mao, R.: Influential community search in large networks. Proc. VLDB Endow. 8(5), 509–520 (2015)
Liu, F., Xue, S., Wu, J., Zhou, C., Hu, W., Paris, C., Nepal, S., Yang, J., Yu, P.S.: Deep learning for community detection: progress, challenges and opportunities. In: IJCAI, pp. 4981–4987 (2020)
Luxburg, U.V.: A tutorial on spectral clustering. Stat. Comput. 17(4), 395–416 (2004)
Meusel, R., Mika, P., Blanco, R.: Focused crawling for structured data. In: CIKM, pp. 1039–1048 (2014)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: NIPS, pp. 3111–3119 (2013)
Pham, K., Santos, A.S.R., Freire, J.: Bootstrapping domain-specific content discovery on the web. In: WWW, pp. 1476–1486 (2019)
Shchur, O., Günnemann, S.: Overlapping community detection with graph neural networks. CoRR (2019). arXiv:1909.12201
Sozio, M., Gionis, A.: The community-search problem and how to plan a successful cocktail party. In: SIGKDD, pp. 939–948 (2010)
Vandenhende, S., Georgoulis, S., Gansbeke, W.V., Proesmans, M., Gool, L.V.: Multi-task learning for dense prediction tasks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. PP(99), 1–1 (2021)
Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. In: ICLR (2018)
Wang, C., Chang, K., Wang, P., Qin, T., Guan, X.: Heterogeneous network crawling: reaching target nodes by motif-guided navigation. IEEE Trans. Knowl. Data Eng. PP(99), 1–1 (2020)
Wu, Y., Zhao, J., Sun, R., Chen, C., Wang, X.: Efficient personalized influential community search in large networks. Data Sci. Eng. 6(3), 310–22 (2021). https://doi.org/10.1007/s41019-021-00163-3
Yang, J., Leskovec, J.: Defining and evaluating network communities based on ground-truth. In: ICDM, pp. 745–754 (2012)
Zheng, L., Li, Z., Li, J., Li, Z., Gao, J.: Addgraph: anomaly detection in dynamic graph using attention-based temporal GCN. In: IJCAI, pp. 4419–4425 (2019)
Zhou, J., Cui, G., Zhang, Z., Yang, C., Liu, Z., Sun, M.: Graph neural networks: a review of methods and applications. CoRR (2018). arXiv:1812.08434
Acknowledgements
We would like to thank Dr. Yixiang Fang for sharing ACQ codes and thank Dr. Xin Huang for sharing their executable LocATC codes. We would like to thank the comments from anonymous reviewers. This work was partially supported by NSFC under Grant No. 61832001.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Chen, J., Gao, J. & Cui, B. ICS-GNN\(^+\): lightweight interactive community search via graph neural network. The VLDB Journal 32, 447–467 (2023). https://doi.org/10.1007/s00778-022-00754-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00778-022-00754-0