---
title: "Dual Contrastive Graph-Level Clustering with Multiple Cluster Perspectives Alignment"
authors:
  - "Jinyu Cai"
  - "Yunhe Zhang"
  - "Jicong Fan"
  - "Yali Du"
  - "Wenzhong Guo"
doi: "10.24963/ijcai.2024/417"
url: "https://ijcai.org/proceedings/2024/417"
pdf: "https://ijcai.org/proceedings/2024/0417.pdf"
venue: "Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence"
year: 2024
pages: "3770-3779"
track: "Main Track"
keywords:
  - "Machine Learning: ML: Clustering"
  - "Machine Learning: ML: Unsupervised learning"
---

# Dual Contrastive Graph-Level Clustering with Multiple Cluster Perspectives Alignment

Jinyu Cai, Yunhe Zhang, Jicong Fan, Yali Du, Wenzhong Guo

*Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence*, pages 3770-3779. DOI: [10.24963/ijcai.2024/417](https://doi.org/10.24963/ijcai.2024/417)

## Abstract

Graph-level clustering, which is essential in medical, biomedical, and social network data analysis, aims to group a set of graphs into various clusters.   However, existing methods generally rely on a single clustering criterion, e.g., $k$-means, which limits their abilities to fully exploit the complex Euclidean and structural information inherent in graphs. To bridge this gap, we propose a dual contrastive graph-level clustering (DCGLC) method in this paper. DCGLC leverages graph contrastive learning and introduces the Euclidian-based and subspace-based cluster heads to capture the cluster information from different cluster perspectives. To overcome the inconsistency estimations and fuse the cluster information of multiple cluster heads, we propose a contrastive mechanism to align the cluster information derived from them. The cluster-perspective contrast facilitates the capture of more comprehensive cluster information. Importantly, DCGLC is an end-to-end framework in which graph contrastive learning and cluster-perspective contrast are mutually improved. We demonstrate the superiority of DCGLC over the state-of-the-art baselines on numerous graph benchmarks.