[1]GAO Xiaofang,JIA Zonghan,LIANG Jiye.Contrastive clustering algorithm based on trend consistency learning[J].CAAI Transactions on Intelligent Systems,2026,21(2):389-398.[doi:10.11992/tis.202506027]
Copy

Contrastive clustering algorithm based on trend consistency learning

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 21 Number of periods: 2026 2 Page number: 389-398 Column: 学术论文—机器学习 Public date: 2026-05-16
Title:
Contrastive clustering algorithm based on trend consistency learning
Author(s):
GAO Xiaofang1;  JIA Zonghan1;  LIANG Jiye1; 2
1. School of Computer and Information Technology, Shanxi University, Taiyuan 030006, China;
2. Laboratory of Computational Intelligence and Chinese Processing, Ministry of Education, Taiyuan 030006, China
Keywords:
contrast clustering; contrastive learning; false negatives; trend consistency; pseudo labels; semantic information; inter-class distinguishability; mask matrix
CLC:
TP18
DOI:
10.11992/tis.202506027
Abstract:
In recent years, contrastive clustering has become a research hotspot in the fields of data mining and machine learning, aiming to enhance clustering performance by leveraging the powerful feature representation capabilities of contrastive learning. However, the use of contrastive learning often introduces the problem of false negative examples due to category conflicts, thereby reducing the performance of contrastive clustering. To address this issue, this paper proposes a contrastive clustering algorithm based on a trend consistency constraint strategy (CCTC). By marking high-confidence sample pairs with consistent category information in the trend consistency array and using this semantic information to calculate the trend constraint matrix to assist in selecting positive samples, the algorithm achieves dynamic interaction between cluster-level and instance-level sample information through the combination of instance-level and cluster-level consistency loss functions, thereby enhancing sample consistency and inter-class distinguishability. Compared with other contrastive clustering algorithms, this method can utilize the pseudo-label change trends in the multi-round training process to obtain sample pairs with high-confidence category trend consistency, thus improving the clustering performance of the model. Experiments have demonstrated the effectiveness of the algorithm.
References:
[1] 蒋树强, 闵巍庆, 王树徽. 面向智能交互的图像识别技术综述与展望[J]. 计算机研究与发展, 2016, 53(1): 113-122 JIANG Shuqiang, MIN Weiqing, WANG Shuhui. Survey and prospect of intelligent interaction-oriented image recognition techniques[J]. Journal of computer research and development, 2016, 53(1): 113-122
[2] 王科俊, 赵彦东, 邢向磊. 深度学习在无人驾驶汽车领域应用的研究进展[J]. 智能系统学报, 2018, 13(1): 55-69 WANG Kejun, ZHAO Yandong, XING Xianglei. Deep learning in driverless vehicles[J]. CAAI transactions on intelligent systems, 2018, 13(1): 55-69
[3] S?NCHEZ-FERRERA A, CALVO B, LOZANO J A. A review on self-supervised learning for time series anomaly detection: recent advances and open challenges[EB/OL]. (2025-01-25)[2025-06-24]. https://arxiv.org/abs/2501.15196.
[4] 姬强, 孙艳丰, 胡永利, 等. 深度聚类算法研究综述[J]. 北京工业大学学报, 2021, 47(8): 912-924 JI Qiang, SUN Yanfeng, HU Yongli, et al. Review of clustering with deep learning[J]. Journal of Beijing University of Technology, 2021, 47(8): 912-924
[5] 张慧, 王坤峰, 王飞跃. 深度学习在目标视觉检测中的应用进展与展望[J]. 自动化学报, 2017, 43(8): 1289-1305 ZHANG Hui, WANG Kunfeng, WANG Feiyue. Advances and perspectives on applications of deep learning in visual object detection[J]. Acta automatica sinica, 2017, 43(8): 1289-1305
[6] 赵永强, 饶元, 董世鹏, 等. 深度学习目标检测方法综述[J]. 中国图象图形学报, 2020, 25(4): 629-654 ZHAO Yongqiang, RAO Yuan, DONG Shipeng, et al. Survey on deep learning object detection[J]. Journal of image and graphics, 2020, 25(4): 629-654
[7] 侯海薇, 丁世飞, 徐晓. 基于无监督表征学习的深度聚类研究进展[J]. 模式识别与人工智能, 2022, 35(11): 999-1014 HOU Haiwei, DING Shifei, XU Xiao. Research progress of deep clustering based on unsupervised representation learning[J]. Pattern recognition and artificial intelligence, 2022, 35(11): 999-1014
[8] 陈俊芬, 赵佳成, 翟俊海, 等. 基于无监督学习视觉特征的深度聚类方法[J]. 南京航空航天大学学报, 2021, 53(5): 718-725 CHEN Junfen, ZHAO Jiacheng, ZHAI Junhai, et al. Deep clustering method based on unsupervised visual features learning[J]. Journal of Nanjing University of Aeronautics & Astronautics, 2021, 53(5): 718-725
[9] CHIEN J T, CHEN Kuan. False negative masking for debiasing in contrastive learning[C]//2024 International Joint Conference on Neural Networks. Yokohama: IEEE, 2024: 1-6.
[10] KIM S, JANG H. LinkFND: simple framework for false negative detection in recommendation tasks with graph contrastive learning[J]. IEEE access, 2023, 11: 145308-145319
[11] DWIBEDI D, AYTAR Y, TOMPSON J, et al. With a little help from my friends: nearest-neighbor contrastive learning of visual representations[C]//2021 IEEE/CVF International Conference on Computer Vision. Montreal: IEEE, 2022: 9568-9577.
[12] ZHUANG Chengxu, ZHAI A, YAMINS D. Local aggregation for unsupervised learning of visual embeddings[C]//2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2019: 6001-6011.
[13] CHEN T S, HUNG W C, TSENG H Y, et al. Incremental false negative detection for contrastive learning[EB/OL]. (2021-06-07)[2025-06-24]. https://arxiv.org/abs/2106.03719.
[14] XU Lingling, XIE Haoran, WANG F L, et al. Contrastive sentence representation learning with adaptive false negative cancellation[J]. Information fusion, 2024, 102: 102065
[15] GIDARIS S, BURSUC A, KOMODAKIS N, et al. Learning representations by predicting bags of visual words[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 6926-6936.
[16] LI Yunfan, HU Peng, LIU Zitao, et al. Contrastive clustering[J]. Proceedings of the AAAI conference on artificial intelligence, 2021, 35(10): 8547-8555
[17] LI Yunfan, YANG Mouxing, PENG Dezhong, et al. Twin contrastive learning for online clustering[J]. International journal of computer vision, 2022, 130(9): 2205-2221
[18] NIU Chuang, SHAN Hongming, WANG Ge. Spice: semantic pseudo-labeling for image clustering[J]. IEEE transactions on image processing, 2022, 31: 7264-7278
[19] DANG Zhiyuan, DENG Cheng, YANG Xu, et al. Nearest neighbor matching for deep clustering[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 13693-13702.
[20] CHEN Ting, KORNBLITH S, NOROUZI M, et al. A simple framework for contrastive learning of visual representations[EB/OL]. (2020-02-13)[2025-06-24]. https://arxiv.org/abs/2002.05709.
[21] ZHONG Huasong, WU Jianlong, CHEN Chong, et al. Graph contrastive clustering[C]//2021 IEEE/CVF International Conference on Computer Vision. Montreal: IEEE, 2021: 9204-9213.
[22] SHI Jianbo, MALIK J. Normalized cuts and image segmentation[J]. IEEE transactions on pattern analysis and machine intelligence, 2000, 22(8): 888-905
[23] CHIDANANDA GOWDA K, KRISHNA G. Agglomerative clustering using the concept of mutual nearest neighbourhood[J]. Pattern recognition, 1978, 10(2): 105-112
[24] CAI Deng, HE Xiaofei, WANG Xuanhui, et al. Locality preserving nonnegative matrix factorization[C]//Proceedings of the 21st International Joint Conference on Artificial Intelligence. San Francisco: Morgan Kaufmann Publishers Inc. , 2009: 1010-1015.
[25] BENGIO Y, LAMBLIN P, POPOVICI D, et al. Greedy layer-wise training of deep networks[C]//Advances in Neural Information Processing Systems 19. Cambridge: The MIT Press, 2007: 153-160.
[26] VINCENT P, LAROCHELLE H, LAJOIE I, et al. Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion[J]. Journal of machine learning research, 2010, 11(12).
[27] RADFORD A, METZ L, CHINTALA S. Unsupervised representation learning with deep convolutional generative adversarial networks[EB/OL]. (2015-11-19) [2025-06-24]. https://arxiv.org/abs/1511.06434.
[28] ZEILER M D, KRISHNAN D, TAYLOR G W, et al. Deconvolutional networks[C]//2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco: IEEE, 2010: 2528-2535.
[29] KINGMA D P, WELLING M. Auto-encoding variational Bayes[EB/OL]. (2013-12-20) [2025-06-24]. https://arxiv.org/abs/1312.6114.
[30] XIE Junyuan, GIRSHICK R, FARHADI A. Unsupervised deep embedding for clustering analysis[EB/OL]. (2015-11-19) [2025-06-24]. https://arxiv.org/abs/1511.06335.
[31] YANG Jianwei, PARIKH D, BATRA D. Joint unsupervised learning of deep representations and image clusters[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 5147-5156.
[32] CHANG J, WANG L, MENG G, et al. Deep adaptive image clustering[C]//Proceedings of the IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 5879-5887.
[33] WU J, LONG K, WANG F, et al. Deep comprehensive correlation mining for image clustering[C]//Proceedings of the IEEE/CVF International Conference On Computer vision. Seoul: IEEE, 2019: 8150-8159.
[34] HUANG Jiabo, GONG Shaogang, ZHU Xiatian. Deep semantic clustering by partition confidence maximisation[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 8846-8855.
[35] ZHONG Huasong, CHEN Chong, JIN Zhongming, et al. Deep robust clustering by contrastive learning[EB/OL]. (2020-08-07)[2025-06-24]. https://arxiv.org/abs/2008.03030.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems