Community Detection Clustering via Gumbel Softmax
- PDF / 2,592,267 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 26 Downloads / 221 Views
ORIGINAL RESEARCH
Community Detection Clustering via Gumbel Softmax Deepak Bhaskar Acharya1 · Huaming Zhang1 Received: 16 May 2020 / Accepted: 21 July 2020 © Springer Nature Singapore Pte Ltd 2020
Abstract Recently, in many systems such as speech recognition and visual processing, deep learning has been widely implemented. In this research, we are exploring the possibility of using deep learning in community detection among the graph datasets. Graphs have gained growing traction in different fields, including social networks, information graphs, the recommender system, and also life sciences. In this paper, we propose a method of community detection clustering the nodes of various graph datasets. We cluster different category datasets that belong to affiliation networks, animal networks, human contact networks, human social networks, miscellaneous networks. The deep learning role in modeling the interaction between nodes in a network allows a revolution in the field of science relevant to graph network analysis. In this paper, we extend the gumbel softmax approach to graph network clustering. The experimental findings on specific graph datasets reveal that the new approach outperforms traditional clustering significantly, which strongly shows the efficacy of deep learning in graph community detection clustering. We do a series of experiments on our graph clustering algorithm, using various graph datasets: Zachary’s karate club, Highland tribes, Train bombing, American Revolution, Dolphins, Zebra, Windsurfers, Les Misérables, Political books. Keywords Community detection · Gumbel softmax · Graph node clustering · Machine learning · Deep learning
Introduction Deep learning has become a hot topic in machine learning and artificial intelligence fields. In specific tasks such as speech recognition, natural language processing, image processing, and large-scale training frameworks for deep learning have been developed and widely implemented. The use of deep learning in community detection clustering has not yet been thoroughly studied, to our knowledge. The goal of this research is to carry out some preliminary research along that path. Communication can be a human social networks, affiliation networks, animal networks, or human contact networks. Moreover, it is a subject of great interest in its economic and marketing implications to discover and analyze the community structure. For example, the advertisement can * Deepak Bhaskar Acharya [email protected] Huaming Zhang [email protected] 1
Computer Science Department, The University of Alabama in Huntsville, Huntsville, AL 35806, USA
be enhanced by recognizing and targeting the most active users of any community, taking advantage of effects such as word of mouth, and spreading information within the group. Likewise, it may be efficient to take advantage of user affiliations with communities to provide useful recommendations based on shared interests with their friends. Particularly in the expansion of information growth, a vast field of research has emerged and has
Data Loading...
