.png){kind=icon}
.png){kind=icon}
Return
Parameter-Agnostic Deep Graph Clustering
.png){kind=icon}
PRE
AI
DOI：10.1145/3633783.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Deep graph clustering, efficiently dividing nodes into multiple disjoint clusters in an unsupervised manner, has become a crucial tool for analyzing ubiquitous graph data. Existing methods have acquired impressive clustering effects by optimizing the clustering network under the parametric condition-predefining the true number of clusters (Ktr). However, Ktr is inaccessible in pure unsupervised scenarios, in which existing methods are incapable of inferring the number of clusters (K), causing limited feasibility. This article proposes the first Parameter-Agnostic Deep Graph Clustering method (PADGC), which consists of two core modules: K-guidence clustering and topological-hierarchical inference, to infer K efficiently and gain impressive clustering predictions. Specifically, K-guidence clustering is employed to optimize the cluster assignments and discriminative embeddings in a mutual promotion manner under the latest updated K, even though K may deviate from Ktr. In turn, such optimized cluster assignments are utilized to explore more accurate K in the topological-hierarchical inference, which can split the dispersive clusters and merge the coupled ones. In this way, these two modules are complementarily optimized until generating the final convergent K and discriminative cluster assignments. Extensive experiments on several benchmarks, including graphs and images, can demonstrate the superiority of our method. The mean values of our inferred K, in 11 out of 12 datasets, deviates from Ktr by less than 1. Our method can also achieve competitive clustering effects with existing parametric deep graph clustering.
Keywords:
Parameter-agnostic graph clustering
topological-hierarchical inference
K-guidence clustering
deep graph clustering
Journal
IF:
4.8
Papers:
1.3K
Citations:
4.4K