Reinforcement Graph Clustering with Unknown Cluster Number

TL;DR

This paper introduces Reinforcement Graph Clustering (RGC), a novel deep graph clustering approach that automatically determines the number of clusters using reinforcement learning, eliminating the need for predefined cluster numbers.

Contribution

The proposed RGC method unifies cluster number determination and representation learning into a reinforcement learning framework, enabling unsupervised graph clustering without prior knowledge of cluster count.

Findings

RGC effectively determines the optimal number of clusters.

The method improves clustering cohesion and separation.

Experiments show RGC outperforms existing methods in accuracy and efficiency.

Abstract

Deep graph clustering, which aims to group nodes into disjoint clusters by neural networks in an unsupervised manner, has attracted great attention in recent years. Although the performance has been largely improved, the excellent performance of the existing methods heavily relies on an accurately predefined cluster number, which is not always available in the real-world scenario. To enable the deep graph clustering algorithms to work without the guidance of the predefined cluster number, we propose a new deep graph clustering method termed Reinforcement Graph Clustering (RGC). In our proposed method, cluster number determination and unsupervised representation learning are unified into a uniform framework by the reinforcement learning mechanism. Concretely, the discriminative node representations are first learned with the contrastive pretext task. Then, to capture the clustering state accurately with both local and global information in the graph, both node and cluster states are considered. Subsequently, at each state, the qualities of different cluster numbers are evaluated by the quality network, and the greedy action is executed to determine the cluster number. In order to conduct feedback actions, the clustering-oriented reward function is proposed to enhance the cohesion of the same clusters and separate the different clusters. Extensive experiments demonstrate the effectiveness and efficiency of our proposed method. The source code of RGC is shared at https://github.com/yueliu1999/RGC and a collection (papers, codes and, datasets) of deep graph clustering is shared at https://github.com/yueliu1999/Awesome-Deep-Graph-Clustering on Github.