Weighted Graph Nodes Clustering via Gumbel Softmax

TL;DR

This paper introduces WGCGS, a novel graph clustering algorithm using Gumbel Softmax, which efficiently identifies clusters in weighted graphs, demonstrated on the Karate club network with promising results.

Contribution

The paper presents a new weighted graph clustering method using Gumbel Softmax, showing improved effectiveness over existing algorithms on real datasets.

Findings

WGCGS effectively clusters the Karate club weighted network.

The algorithm outperforms some state-of-the-art graph clustering methods.

Experimental results validate the efficiency and accuracy of WGCGS.

Abstract

Graph is a ubiquitous data structure in data science that is widely applied in social networks, knowledge representation graphs, recommendation systems, etc. When given a graph dataset consisting of one graph or more graphs, where the graphs are weighted in general, the first step is often to find clusters in the graphs. In this paper, we present some ongoing research results on graph clustering algorithms for clustering weighted graph datasets, which we name as Weighted Graph Node Clustering via Gumbel Softmax (WGCGS for short). We apply WGCGS on the Karate club weighted network dataset. Our experiments demonstrate that WGCGS can efficiently and effectively find clusters in the Karate club weighted network dataset. Our algorithm's effectiveness is demonstrated by (1) comparing the clustering result obtained from our algorithm and the given labels of the dataset; and (2) comparing various metrics between our clustering algorithm and other state-of-the-art graph clustering algorithms.