RGCLN: Relational Graph Convolutional Ladder-Shaped Networks for Signed Network Clustering
Source abstract
Abstract
Node embeddings are increasingly used in various analysis tasks of networks due to their excellent dimensional compression and feature representation capabilities. However, most researchers’ priorities have always been link prediction, which leads to signed network clustering being under-explored. Therefore, we propose an asymmetric ladder-shaped architecture called RGCLN based on multi-relational graph convolution that can fuse deep node features to generate node representations with great representational power. RGCLN adopts a deep framework to capture and convey information instead of using the common method in signed networks—balance theory. In addition, RGCLN adds a size constraint to the loss function to prevent image-like overfitting during the unsupervised learning process. Based on the node features learned by this end-to-end trained model, RGCLN performs community detection in a large number of real-world networks and generative networks, and the results indicate that our model has an advantage over state-of-the-art network embedding algorithms.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Graph Neural Networks · Complex Network Analysis Techniques · Bioinformatics and Genomic Networks
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science and Engineering, Shanghai University, Shanghai 200444, China
References (42)
Show source-provided references
1. Leskovec, J., Huttenlocher, D., and Kleinberg, J. (2010, January 10–15). Signed networks in social media. Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, Atlanta, GA, USA.10.1145/1753326.1753532 ↗
2. Liu, H., Zhang, Z., Cui, P., Zhang, Y., Cui, Q., Liu, J., and Zhu, W. (2021, January 14–18). Signed Graph Neural Network with Latent Groups. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Virtual Event.10.1145/3447548.3467355 ↗
3. Javari, A., Derr, T., Esmailian, P., Tang, J., and Chang, K.C.C. (2020, January 20–24). Rose: Role-based signed network embedding. Proceedings of the Web Conference 2020, Taipei, Taiwan.10.1145/3366423.3380038 ↗
4. Chen, Y., Qian, T., Liu, H., and Sun, K. (2018, January 22–26). “Bridge”: Enhanced Signed Directed Network Embedding. Proceedings of the 27th ACM International Conference on Information and Knowledge Management, Torino, Italy.10.1145/3269206.3271738 ↗
5. Xu, P., Hu, W., Wu, J., Liu, W., Du, B., and Yang, J. (2019, January 8–11). Social trust network embedding. Proceedings of the 2019 IEEE International Conference on Data Mining (ICDM), Beijing, China.10.1109/ICDM.2019.00078 ↗
6. Lee, Y.C., Seo, N., Han, K., and Kim, S.W. (2020, January 25–30). ASiNE: Adversarial Signed Network Embedding. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event.10.1145/3397271.3401079 ↗
7. Decoupled variational embedding for signed directed networks
8. Muse: Multi-faceted attention for signed network embedding10.1016/j.neucom.2022.11.021 ↗
9. Snegan: Signed network embedding by using generative adversarial nets10.1109/TETCI.2020.3035937 ↗
10. Wang, S., Aggarwal, C., Tang, J., and Liu, H. (2017, January 6–10). Attributed signed network embedding. Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, Singapore.10.1145/3132847.3132905 ↗
11. Community mining from signed social networks10.1109/TKDE.2007.1061 ↗
12. Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., and Mei, Q. (2015, January 18–22). Line: Large-scale information network embedding. Proceedings of the 24th International Conference on World Wide Web, Florence, Italy.10.1145/2736277.2741093 ↗
13. Cucuringu, M., Davies, P., Glielmo, A., and Tyagi, H. (2019, January 16–18). SPONGE: A generalized eigenproblem for clustering signed networks. Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, Naha, Japan.
14. Mercado, P., Tudisco, F., and Hein, M. (2016). Clustering signed networks with the geometric mean of Laplacians. Adv. Neural Inf. Process. Syst., 29.
15. Heider, F. (2013). The Psychology of Interpersonal Relations, Psychology Press.10.4324/9780203781159 ↗
16. Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015, Springer.10.1007/978-3-319-24574-4_28 ↗
17. Hu, R., Pan, S., Long, G., Lu, Q., Zhu, L., and Jiang, J. (2020, January 7–12). Going deep: Graph convolutional ladder-shape networks. Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, New York, NY, USA.10.1609/aaai.v34i03.5673 ↗
18. Grover, A., and Leskovec, J. (2016, January 13–17). node2vec: Scalable feature learning for networks. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939754 ↗
19. Wang, X., Cui, P., Wang, J., Pei, J., Zhu, W., and Yang, S. (2017, January 4–9). Community preserving network embedding. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.10.1609/aaai.v31i1.10488 ↗
20. Mikolov, T., Chen, K., Corrado, G., and Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv.
21. Transfer independently together: A generalized framework for domain adaptation10.1109/TCYB.2018.2820174 ↗
22. Kunegis, J., Schmidt, S., Lommatzsch, A., Lerner, J., De Luca, E.W., and Albayrak, S. (May, January 29). Spectral analysis of signed graphs for clustering, prediction and visualization. Proceedings of the 2010 SIAM International Conference on Data Mining, Columbus, OH, USA.10.1137/1.9781611972801.49 ↗
23. Chiang, K.Y., Whang, J.J., and Dhillon, I.S. (November, January 29). Scalable clustering of signed networks using balance normalized cut. Proceedings of the 21st ACM International Conference on Information and Knowledge Management, Maui, HI, USA.
24. Zheng, Q., and Skillicorn, D.B. (May, January 30). Spectral embedding of signed networks. Proceedings of the 2015 SIAM International Conference on Data Mining, Vancouver, BC, Canada.10.1137/1.9781611974010.7 ↗
25. Derr, T., Ma, Y., and Tang, J. (2018, January 17–20). Signed graph convolutional networks. Proceedings of the 2018 IEEE International Conference on Data Mining (ICDM), Singapore.10.1109/ICDM.2018.00113 ↗
26. Deep network embedding for graph representation learning in signed networks10.1109/TCYB.2018.2871503 ↗
27. Huang, J., Shen, H., Hou, L., and Cheng, X. (2021, January 2–9). SDGNN: Learning node representation for signed directed networks. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual Event.10.1609/aaai.v35i1.16093 ↗
28. Derr, T., Aggarwal, C., and Tang, J. (2018, January 22–26). Signed network modeling based on structural balance theory. Proceedings of the 27th ACM International Conference on Information and Knowledge Management, Torino, Italy.10.1145/3269206.3271746 ↗
29. Jung, J., Yoo, J., and Kang, U. (2020). Signed Graph Diffusion Network. arXiv.
30. Kim, J., Park, H., Lee, J.E., and Kang, U. (2018, January 23–27). Side: Representation learning in signed directed networks. Proceedings of the 2018 World Wide Web Conference, Lyon, France.10.1145/3178876.3186117 ↗
31. Kumar, S., Spezzano, F., Subrahmanian, V.S., and Faloutsos, C. (2016, January 12–15). Edge weight prediction in weighted signed networks. Proceedings of the 2016 IEEE 16th International Conference on Data Mining (ICDM), Barcelona, Spain.10.1109/ICDM.2016.0033 ↗
32. Li, Y., Tian, Y., Zhang, J., and Chang, Y. (2020, January 7–12). Learning signed network embedding via graph attention. Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, New York, NY, USA.
33. He, Y., Reinert, G., Wang, S., and Cucuringu, M. (2022, January 28–30). SSSNET: Semi-Supervised Signed Network Clustering. Proceedings of the 2022 SIAM International Conference on Data Mining (SDM), Virtual Event.10.1137/1.9781611977172.28 ↗
34. Tian, Y., Zhao, L., Peng, X., and Metaxas, D. (2019). Rethinking kernel methods for node representation learning on graphs. Adv. Neural Inf. Process. Syst., 32.
35. Sampson, S.F. (1968). A Novitiate in a Period of Change: An Experimental and Case Study of Social Relationships. [Ph.D. Thesis, Cornell University].
36. Climate inference on daily rainfall across the Australian continent, 1876–201510.1214/18-AOAS1218 ↗
37. (2021, January 19). Yahoo! Finance. S&P 1500 Data. Available online: https://finance.yahoo.com/.
38. Integrating protein-protein interaction networks with phenotypes reveals signs of interactions10.1038/nmeth.2733 ↗
39. Normalized cuts and image segmentation, Pattern Analysis and Machine Intelligence10.1109/34.868688 ↗
40. The impact of random models on clustering similarity
41. Finding communities in linear time: A physics approach10.1140/epjb/e2004-00125-x ↗
42. Objective criteria for the evaluation of clustering methods10.1080/01621459.1971.10482356 ↗