Abstract
Signed graph neural networks learn low-dimensional representations for nodes in signed networks with positive and negative links, which helps with many downstream tasks like link prediction. However, most existing signed graph neural networks ignore individual characteristics of nodes and thus limit the ability to learn the underlying structure of real signed graphs. To address this limitation, a deep graph neural network framework SiNP to learn Signed network embedding with Node Polarity is proposed. To be more explicit, a node-signed property metric mechanism is developed to encode the individual characteristics of the nodes. In addition, a graph convolution layer is added so that both positive and negative information from neighboring nodes can be combined. The final embedding of nodes is produced by concatenating the outcomes of these two portions. Finally, extensive experiments have been conducted on four significant real-world signed network datasets to demonstrate the efficiency and superiority of the proposed method in comparison to the state-of-the-art.
Subject
General Physics and Astronomy
Reference26 articles.
1. A graph neural network framework for social recommendations;Fan;IEEE Trans. Knowl. Data Eng.,2020
2. Testing for Balance in Social Networks;Feng;J. Am. Stat. Assoc.,2022
3. Dhelim, S., Aung, N., Kechadi, T., Ning, H., Chen, L., and Lakas, A. (2021). Trust2Vec: Large-Scale IoT Trust Management System based on Signed Network Embeddings. IEEE Internet Things J.
4. Mara, A., Mashayekhi, Y., Lijffijt, J., and De Bie, T. (2020, January 19–23). Csne: Conditional signed network embedding. Proceedings of the 29th ACM International Conference on Information & Knowledge Management, Virtual Event.
5. Wang, S., Tang, J., Aggarwal, C., Chang, Y., and Liu, H. (2017, January 27–29). Signed network embedding in social media. Proceedings of the 2017 SIAM International Conference on Data Mining, Houston, TX, USA.