RGCLN: Relational Graph Convolutional Ladder-Shaped Networks for Signed Network Clustering
-
Published:2023-01-19
Issue:3
Volume:13
Page:1367
-
ISSN:2076-3417
-
Container-title:Applied Sciences
-
language:en
-
Short-container-title:Applied Sciences
Author:
Song Anping,Ji Ruyi,Qi Wendong,Zhang Chenbei
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.
Subject
Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science
Reference42 articles.
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. 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. 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. 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. 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.
|
|