Reinforcement Graph Clustering with Unknown Cluster Number

被引:9
作者
Liu, Yue [1 ]
Liang, Ke [1 ]
Xia, Jun [2 ]
Yang, Xihong [1 ]
Zhou, Sihang [1 ]
Liu, Meng [1 ]
Liu, Xinwang [1 ]
Li, Stan Z. [2 ]
机构
[1] NUDT, Changsha, Hunan, Peoples R China
[2] Westlake Univ, Hangzhou, Zhejiang, Peoples R China
来源
PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023 | 2023年
基金
国家重点研发计划; 中国国家自然科学基金;
关键词
Attribute Graph Clustering; Unknown Cluster Number; Reinforcement Learning; Graph Neural Network;
D O I
10.1145/3581783.3612155
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页码:3528 / 3537
页数:10
相关论文
共 50 条
[41]   Reinforcement Routing on Proximity Graph for Efficient Recommendation [J].
Feng, Chao ;
Lian, Defu ;
Wang, Xiting ;
Liu, Zheng ;
Xie, Xing ;
Chen, Enhong .
ACM TRANSACTIONS ON INFORMATION SYSTEMS, 2023, 41 (01)
[42]   A Reinforcement Learning Approach for Graph Rule Learning [J].
Mai, Zhenzhen ;
Wang, Wenjun ;
Liu, Xueli ;
Feng, Xiaoyang ;
Wang, Jun ;
Fu, Wenzhi .
BIG DATA MINING AND ANALYTICS, 2025, 8 (01) :31-44
[43]   Recommendations Based on Reinforcement Learning and Knowledge Graph [J].
Song, Wei ;
Wang, Tichang ;
Zhang, Zihan .
ADVANCES AND TRENDS IN ARTIFICIAL INTELLIGENCE. THEORY AND APPLICATIONS, IEA/AIE 2023, PT I, 2023, 13925 :313-324
[44]   Cluster-HGNN: Deep Local Features Clustering for Few-Shot Image Classification With Hybrid Graph Neural Networks [J].
Wu, Hongxuan ;
Xin, Like .
IEEE ACCESS, 2025, 13 :30965-30975
[45]   Deep Clustering by Graph Attention Contrastive Learning [J].
Liu, Ming ;
Liu, Cong ;
Fu, Xiaoyuan ;
Wang, Jing ;
Li, Jiankun ;
Qi, Qi ;
Liao, Jianxin .
ELECTRONICS, 2023, 12 (11)
[46]   CONVERT: Contrastive Graph Clustering with Reliable Augmentation [J].
Yang, Xihong ;
Tan, Cheng ;
Liu, Yue ;
Liang, Ke ;
Wang, Siwei ;
Zhou, Sihang ;
Xia, Jun ;
Li, Stan Z. ;
Liu, Xinwang ;
Zhu, En .
PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, :319-327
[47]   Graph clustering network with structure embedding enhanced [J].
Ding, Shifei ;
Wu, Benyu ;
Xu, Xiao ;
Guo, Lili ;
Ding, Ling .
PATTERN RECOGNITION, 2023, 144
[48]   Multi-scale graph clustering network [J].
Li, Xiulai ;
Wu, Wei ;
Zhang, Bin ;
Peng, Xin .
INFORMATION SCIENCES, 2024, 678
[49]   Reinforcement Learning of Graph Neural Networks for Service Function Chaining in Computer Network Management [J].
Heo, DongNyeong ;
Lee, Doyoung ;
Kim, Hee-Gon ;
Park, Suhyun ;
Choi, Heeyoul .
2022 23RD ASIA-PACIFIC NETWORK OPERATIONS AND MANAGEMENT SYMPOSIUM (APNOMS 2022), 2022, :139-144
[50]   An efficient leakage power optimization framework based on reinforcement learning with graph neural network [J].
Cao, Peng ;
Dong, Yuhan ;
Zhang, Zhanhua ;
Ding, Wenjie ;
Wang, Jiahao .
SCIENTIFIC REPORTS, 2024, 14 (01)