Open Access

ARTICLE

Graph Transformer for Communities Detection in Social Networks

G. Naga Chandrika¹, Khalid Alnowibet², K. Sandeep Kautish³, E. Sreenivasa Reddy⁴, Adel F. Alrasheedi², Ali Wagdy Mohamed^5,6,*
1 Department of Computer Science and Engineering, ANU College of Engineering and Technology, Guntur,522510, India
2 Statistics and Operations Research Department, College of Science, King Saud University, Riyadh, 11451, Kingdom of Saudi Arabia
3 LBEF Campus, Kathmandu, 44600, Nepal
4 Department of Computer Science and Engineering, ANU, Guntur, 522510, India
5 Operations Research Department, Faculty of Graduate Studies for Statistical Research, Cairo University, Giza, 12613, Egypt
6 Wireless Intelligent Networks Center (WINC), School of Engineering and Applied Sciences, Nile University, Giza, 12588, Egypt
* Corresponding Author: Ali Wagdy Mohamed. Email:
(This article belongs to this Special Issue: Artificial Intelligence and Machine Learning Algorithms in Real-World Applications and Theories)

Computers, Materials & Continua 2022, 70(3), 5707-5720. https://doi.org/10.32604/cmc.2022.021186

Received 26 June 2021; Accepted 13 August 2021; Issue published 11 October 2021

Abstract

Graphs are used in various disciplines such as telecommunication, biological networks, as well as social networks. In large-scale networks, it is challenging to detect the communities by learning the distinct properties of the graph. As deep learning has made contributions in a variety of domains, we try to use deep learning techniques to mine the knowledge from large-scale graph networks. In this paper, we aim to provide a strategy for detecting communities using deep autoencoders and obtain generic neural attention to graphs. The advantages of neural attention are widely seen in the field of NLP and computer vision, which has low computational complexity for large-scale graphs. The contributions of the paper are summarized as follows. Firstly, a transformer is utilized to downsample the first-order proximities of the graph into a latent space, which can result in the structural properties and eventually assist in detecting the communities. Secondly, the fine-tuning task is conducted by tuning variant hyperparameters cautiously, which is applied to multiple social networks (Facebook and Twitch). Furthermore, the objective function (cross-entropy) is tuned by L₀ regularization. Lastly, the reconstructed model forms communities that present the relationship between the groups. The proposed robust model provides good generalization and is applicable to obtaining not only the community structures in social networks but also the node classification. The proposed graph-transformer shows advanced performance on the social networks with the average NMIs of 0.67 ± 0.04, 0.198  0.02, 0.228 ± 0.02, and 0.68 ± 0.03 on Wikipedia crocodiles, Github Developers, Twitch England, and Facebook Page-Page networks, respectively.

---

Keywords

Social networks; graph transformer; community detection; graph classification

---