A novel clustering algorithm based on multi-layer features and graph attention networks

被引:4
作者
Hou, Haiwei [1 ]
Ding, Shifei [1 ,2 ]
Xu, Xiao [1 ,2 ]
Ding, Ling [3 ]
机构
[1] China Univ Min & Technol, Sch Comp Sci & Technol, Xuzhou 221116, Peoples R China
[2] Minist Educ Peoples Republ China, Mine Digitizat Engn Res Ctr, Xuzhou 221116, Peoples R China
[3] Tianjin Univ, Coll Intelligence & Comp, Tianjin 300350, Peoples R China
关键词
Graph attention networks; Deep ensemble clustering; Neural network; Unsupervised representation learning; Feature extraction;
D O I
10.1007/s00500-023-07848-z
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Clustering is a fundamental task in the field of data analysis. With the development of deep learning, deep clustering focuses on learning meaningful representation with neural networks. Ensemble clustering algorithms combine multiple base partitions into a robust and better consensus clustering. Current deep ensemble clustering algorithms usually neglect shallow and original features. Besides, rarel algorithms use graph attention networks to explore clustering structures. This paper proposes a novel Clustering algorithm based on Multi-layer Features and Graph attention Networks (CMFGN). CMFGN obtains multi-layer features through the hierarchical convolutional layers. Moreover, CMFGN combines the co-association matrix with original features as the Graph Attention Networks (GAT) input to obtain consensus clustering, which reuses original information and leverages GAT to inherit a good clustering structure. Extensive experimental results show that CMFGN remarkably outputs competitive methods on four challenging image datasets. In particular, CMFGN achieves the ACC of 82.14% on the Digits dataset, which is almost up to 6% performance improvement compared with the best baseline.
引用
收藏
页码:5553 / 5566
页数:14
相关论文
共 50 条
  • [31] A novel sparrow search algorithm based co-correlation graph construction strategy for wind turbine group anomaly identification via graph attention networks
    Wang, Xiaomin
    Zhuang, Xiao
    Zhou, Di
    Ge, Jian
    Xiang, Jiawei
    RELIABILITY ENGINEERING & SYSTEM SAFETY, 2025, 260
  • [32] A Novel Matrix Completion Model Based on the Multi-Layer Perceptron Integrating Kernel Regularization
    Hu, Xuan
    Han, Yongming
    Geng, Zhiqiang
    IEEE ACCESS, 2021, 9 : 67042 - 67050
  • [33] End-to-end methane gas detection algorithm based on transformer and multi-layer perceptron
    Liu, Chang
    Wang, Gang
    Zhang, Chen
    Patimisco, Pietro
    Cui, Ruyue
    Feng, Chaofan
    Sampaolo, Angelo
    Spagnolo, Vincenzo
    Dong, Lei
    Wu, Hongpeng
    OPTICS EXPRESS, 2024, 32 (01) : 987 - 1002
  • [34] Optimizing the learning process of multi-layer perceptrons using a hybrid algorithm based on MVO and SA
    Yilmaz, Omer
    Altun, Adem Alpaslan
    Koklu, Murat
    INTERNATIONAL JOURNAL OF INDUSTRIAL ENGINEERING COMPUTATIONS, 2022, 13 (04) : 617 - 640
  • [35] MULTI-SCALE SPEAKER EMBEDDING-BASED GRAPH ATTENTION NETWORKS FOR SPEAKER DIARISATION
    Kwon, Youngki
    Heo, Hee-Soo
    Jung, Jee-Weon
    Kim, You Jin
    Lee, Bong-Jin
    Chung, Joon Son
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 8367 - 8371
  • [36] Attention-based graph neural networks: a survey
    Chengcheng Sun
    Chenhao Li
    Xiang Lin
    Tianji Zheng
    Fanrong Meng
    Xiaobin Rui
    Zhixiao Wang
    Artificial Intelligence Review, 2023, 56 : 2263 - 2310
  • [37] Predicting Propositional Satisfiability Based on Graph Attention Networks
    Chang, Wenjing
    Zhang, Hengkai
    Luo, Junwei
    INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS, 2022, 15 (01)
  • [38] Predicting Propositional Satisfiability Based on Graph Attention Networks
    Wenjing Chang
    Hengkai Zhang
    Junwei Luo
    International Journal of Computational Intelligence Systems, 15
  • [39] Attention-based graph neural networks: a survey
    Sun, Chengcheng
    Li, Chenhao
    Lin, Xiang
    Zheng, Tianji
    Meng, Fanrong
    Rui, Xiaobin
    Wang, Zhixiao
    ARTIFICIAL INTELLIGENCE REVIEW, 2023, 56 (SUPPL 2) : 2263 - 2310
  • [40] Multi-layer features ensemble soft sensor regression model based on stacked autoencoder and vine copula
    Chen, Hongmin
    Li, Shaojun
    CANADIAN JOURNAL OF CHEMICAL ENGINEERING, 2023, 101 (08) : 4606 - 4619