《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (4): 1021-1028.DOI: 10.11772/j.issn.1001-9081.2021071275
• CCF第36届中国计算机应用大会 (CCF NCCA 2021) • 上一篇
董永峰1,2,3, 邓亚晗1,2,3, 董瑶1,2,3(), 王雅琮1,2,3
收稿日期:
2021-07-16
修回日期:
2021-08-01
接受日期:
2021-08-18
发布日期:
2022-04-15
出版日期:
2022-04-10
通讯作者:
董瑶
作者简介:
董永峰(1977—),男,河北定州人,教授,博士,CCF会员,主要研究方向:人工智能、知识图谱基金资助:
Yongfeng DONG1,2,3, Yahan DENG1,2,3, Yao DONG1,2,3(), Yacong WANG1,2,3
Received:
2021-07-16
Revised:
2021-08-01
Accepted:
2021-08-18
Online:
2022-04-15
Published:
2022-04-10
Contact:
Yao DONG
About author:
DONG Yongfeng, born in 1977, Ph. D., professor. His research interests include artificial intelligence, knowledge graph.Supported by:
摘要:
聚类是一种寻找数据之间内在结构的技术,是许多数据驱动应用领域的一个基本问题,而聚类性能在很大程度上取决于数据表示的质量。近年来,深度学习因其强大的特征提取能力被广泛地应用于聚类任务,以学习更好的特征表示,显著提高了聚类性能。首先,介绍了传统的聚类任务;然后,根据网络结构介绍了基于深度学习的聚类及代表性方法,指出了当前存在的问题,并介绍了基于深度学习的聚类在不同领域的应用;最后,对基于深度学习的聚类发展进行了总结与展望。
中图分类号:
董永峰, 邓亚晗, 董瑶, 王雅琮. 基于深度学习的聚类综述[J]. 计算机应用, 2022, 42(4): 1021-1028.
Yongfeng DONG, Yahan DENG, Yao DONG, Yacong WANG. Survey of clustering based on deep learning[J]. Journal of Computer Applications, 2022, 42(4): 1021-1028.
深度聚类算法 | 损失函数 | 优点 | 缺点 |
---|---|---|---|
基于AE的深度聚类 | 可解释性强 | 对神经网络的深度有限制 | |
基于损失的DNN的深度聚类 | 网络深度不限,适宜大规模数据 | 需谨慎设计聚类损失模型 | |
基于GAN的深度聚类 | 框架灵活 | 模态易崩溃,收敛速度慢 | |
基于VAE的深度聚类 | 有理论保证 | 计算复杂度较高 | |
基于GNN的深度聚类 | 可处理复杂图结构数据 | 缺乏图信息、结构、视图的整体融合,计算复杂度高 |
表1 深度聚类算法总结
Tab. 1 Summary of deep clustering algorithms
深度聚类算法 | 损失函数 | 优点 | 缺点 |
---|---|---|---|
基于AE的深度聚类 | 可解释性强 | 对神经网络的深度有限制 | |
基于损失的DNN的深度聚类 | 网络深度不限,适宜大规模数据 | 需谨慎设计聚类损失模型 | |
基于GAN的深度聚类 | 框架灵活 | 模态易崩溃,收敛速度慢 | |
基于VAE的深度聚类 | 有理论保证 | 计算复杂度较高 | |
基于GNN的深度聚类 | 可处理复杂图结构数据 | 缺乏图信息、结构、视图的整体融合,计算复杂度高 |
算法 | 特点 | 优点 | 缺点 |
---|---|---|---|
亲和矩阵/图学习算法 | 使用统一相似性度量矩阵 | 可直接应用于图结构数据 | 性能高度依赖于相似矩阵 |
子空间学习算法 | 使用统一特征表达 | 良好的特征表达有利于提升 聚类效果,可解释性强 | 性能高度依赖于数据的 初始化及特征表达 |
协同训练算法 | 使用不同视角信息协助其他视角聚类 | 提取信息充分,可处理大规模信息 | 学习多视角信息耗时 |
后融合算法 | 不同视角独立聚类后再融合 实现整体多视角聚类 | 可解释性强 | 共享信息使用不全 |
表2 经典多视角聚类算法的优缺点比较
Tab. 2 Advantage and disadvantage comparison of classical multi-view clustering algorithms
算法 | 特点 | 优点 | 缺点 |
---|---|---|---|
亲和矩阵/图学习算法 | 使用统一相似性度量矩阵 | 可直接应用于图结构数据 | 性能高度依赖于相似矩阵 |
子空间学习算法 | 使用统一特征表达 | 良好的特征表达有利于提升 聚类效果,可解释性强 | 性能高度依赖于数据的 初始化及特征表达 |
协同训练算法 | 使用不同视角信息协助其他视角聚类 | 提取信息充分,可处理大规模信息 | 学习多视角信息耗时 |
后融合算法 | 不同视角独立聚类后再融合 实现整体多视角聚类 | 可解释性强 | 共享信息使用不全 |
1 | 章永来,周耀鉴. 聚类算法综述[J]. 计算机应用, 2019, 39(7):1869-1882. 10.11772/j.issn.1001-9081.2019010174 |
ZHANG Y L, ZHOU Y J. Review of clustering algorithms[J]. Journal of Computer Applications, 2019, 39(7): 1869-1882. 10.11772/j.issn.1001-9081.2019010174 | |
2 | ALJALBOUT E, GOLKOV V, SIDDIQUI Y, et al. Clustering with deep learning: taxonomy and new methods[EB/OL]. (2018-09-13) [2021-01-25].. |
3 | RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088): 533-536. 10.1038/323533a0 |
4 | GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial networks[C]// Proceedings of the 27th International Conference on Neural Information Processing Systems. Cambridge: MIT Press, 2014:2672-2680. |
5 | KINGMA D P, WELLING M. Auto-encoding variational Bayes[EB/OL]. (2014-05-01) [2021-01-25].. 10.1561/9781680836233 |
6 | HUANG P H, HUANG Y, WANG W, et al. Deep embedding network for clustering[C]// Proceedings of the 22nd International Conference on Pattern Recognition. Piscataway: IEEE, 2014: 1532-1537. 10.1109/icpr.2014.272 |
7 | BROWNE M, GHIDARY S S. Convolutional neural networks for image processing: an application in robot vision[C]// Proceedings of the 2003 Australian Joint Conference on Artificial Intelligence, LNCS 2903. Berlin: Springer, 2003:641-652. |
8 | KRUTHIVENTI S S S, AYUSH K, BABU R V. DeepFix: a fully convolutional neural network for predicting human eye fixations[J]. IEEE Transactions on Image Processing, 2017, 26(9):4446-4456. 10.1109/tip.2017.2710620 |
9 | BENGIO Y, LAMBLIN P, POPOVICI D, et al. Greedy layer-wise training of deep networks[C]// Proceedings of the 19th International Conference on Neural Information Processing Systems. Cambridge: MIT Press, 2006:153-160. 10.7551/mitpress/7503.003.0024 |
10 | XIE J Y, GIRSHICK R, FARHADI A. Unsupervised deep embedding for clustering analysis[C]// Proceedings of the 33rd International Conference on Machine Learning. New York: JMLR.org: 2016: 478-487. |
11 | HSU C C, LIN C W. CNN-based joint clustering and representation learning with feature drift compensation for large-scale image data[J]. IEEE Transactions on Multimedia, 2018, 20(2): 421-429. 10.1109/tmm.2017.2745702 |
12 | CHANG J L, WANG L F, MENG G F, et al. Deep adaptive image clustering[C]// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 5880-5888. 10.1109/iccv.2017.626 |
13 | CHEN X, DUAN Y, HOUTHOOFT R, et al. InfoGAN: interpretable representation learning by information maximizing generative adversarial nets[C]// Proceedings of the 30th International Conference on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc., 2016: 2180-2188. |
14 | DILOKTHANAKUL N, MEDIANO P A M, GARNELO M, et al. Deep unsupervised clustering with Gaussian mixture variational autoencoders[EB/OL]. (2017-01-13) [2021-01-25].. |
15 | JIANG Z X, ZHENG Y, TAN H C, et al. Variational deep embedding: an unsupervised and generative approach to clustering[C]// Proceedings of the 26th International Joint Conference on Artificial Intelligence. California: IJCAI Organization, 2017: 1965-1972. 10.24963/ijcai.2017/273 |
16 | SHI J, MALIK J. Normalized cuts and image segmentation[C]// Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 1997: 731. |
17 | NEWMAN M E J, GIRVAN M. Finding and evaluating community structure in networks[J]. Physical Review E, Statistical, Nonlinear, and Soft Matter Physics, 2004, 69(2): No.026113. 10.1103/physreve.69.026113 |
18 | XU X W, YURUK N, FENG Z D, et al. SCAN: a structural clustering algorithm for networks[C]// Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2007: 824-833. 10.1145/1281192.1281280 |
19 | JI Y G, SHI C, FANG Y, et al. Semi-supervised co-clustering on attributed heterogeneous information networks[J]. Information Processing and Management, 2020, 57(6): No.102338. 10.1016/j.ipm.2020.102338 |
20 | WANG C, PAN S R, HU R Q, et al. Attributed graph clustering: a deep attentional embedding approach[C]// Proceedings of the 28th International Joint Conference on Artificial Intelligence. California: IJCAI Organization, 2019: 3670-3676. 10.24963/ijcai.2019/509 |
21 | BO D Y, WANG X, SHI C, et al. Structural deep clustering network[C]// Proceedings of the 2020 Web Conference. New York: ACM, 2020: 1400-1410. 10.1145/3366423.3380214 |
22 | ZHANG X T, LIU H, LI Q M, et al. Attributed graph clustering via adaptive graph convolution[C]// Proceedings of 28th International Joint Conference on Artificial Intelligence. California: IJCAI Organization, 2019: 4327-4333. 10.24963/ijcai.2019/601 |
23 | 康雁,寇勇奇,谢思宇,等.基于融合变分图注意自编码器的深度聚类模型[J].计算机科学,2021,48(S2):81-87,116. 10.11896/jsjkx.210300036 |
KANG Y, KOU Y Q, XIE S Y,et al. Deep clustering model based on fusion variational graph attention self-encoder[J]. Computer Science,2021,48(S2):81-87,116. 10.11896/jsjkx.210300036 | |
24 | 何雪梅. 多视图聚类算法综述[J]. 软件导刊, 2019, 18 (4): 79-81, 86. 10.11907/rjdk.182831 |
HE X M. A Survey of multi-view clustering algorithms[J]. Software Guide, 2019, 18(4): 79-81, 86. 10.11907/rjdk.182831 | |
25 | HU Z N, DONG Y X, WANG K S, et al. GPT-GNN: generative pre-training of graph neural networks[C]// Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2020: 1857-1867. 10.1145/3394486.3403237 |
26 | LIM K L, JIANG X D, YI C Y. Deep clustering with variational autoencoder[J]. IEEE Signal Processing Letters, 2020, 27:231-235. 10.1109/lsp.2020.2965328 |
27 | SONG C F, LIU F, HUANG Y Z, et al. Auto-encoder based data clustering[C]// Proceedings of the 2013 Iberoamerican Congress on Pattern Recognition, LNCS 8258. Berlin: Springer, 2013: 117-124. |
28 | HUANG Q J, ZHANG Y, PENG H, et al. Deep subspace clustering to achieve jointly latent feature extraction and discriminative learning[J]. Neurocomputing, 2020, 404: 340-350. 10.1016/j.neucom.2020.04.120 |
29 | FALCON W, CHO K. A framework for contrastive self-supervised learning and designing a new approach[EB/OL]. (2020-08-31) [2021-01-25].. |
30 | KANG Z, PENG C, CHENG Q, la et. Structured graph learning for clustering and semi-supervised classification[J]. Pattern Recognition, 2021, 110: No.107627. 10.1016/j.patcog.2020.107627 |
31 | ZHU Y Q, XU Y C, YU F, et al. CAGNN: cluster-aware graph neural networks for unsupervised graph representation learning[EB/OL]. (2020-09-03) [2021-02-12].. |
32 | JIA Z, LIN S, YING R, et al. Redundancy-free computation graphs for graph neural networks[C]// Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2020: 997-1005. 10.1145/3394486.3403142 |
33 | 张晨阳,黄腾,吴壮壮. 基于K-Means聚类与深度学习的RGB-D SLAM算法[J]. 计算机工程, 2022, 48(1):236-244, 252. |
ZHANG C Y, HUANG T, WU Z Z. RGB-D SLAM algorithm based on K-means clustering and deep learning[J]. Computer Engineering, 2022, 48(1):236-244, 252 . | |
34 | 向宽,李松松,栾明慧,等. 基于改进Faster RCNN的铝材表面缺陷检测方法[J]. 仪器仪表学报, 2021, 42(1):191-198. 10.1109/icicn52636.2021.9673969 |
XIANG K, LI S S, LUAN M H, et al. Aluminum product surface defect detection method based on improved Faster RCNN[J]. Chinese Journal of Scientific Instrument, 2021, 42(1): 191-198. 10.1109/icicn52636.2021.9673969 | |
35 | 汪繁荣,向堃,吴铁洲. 基于聚类特征及seq2seq深度CNN的家电负荷识别方法研究[J/OL]. 电测与仪表. (2020-10-16) [2021-03-24]., |
XIANG K, WU T Z. Research on household appliance load identification method based on clustering features and seq2seq depth CNN[J/OL]. Electrical Measurement and Instrumentation. (2020-10-16) [2021-03-24]. | |
36 | 杨杰文,章光,陈西江,等. 融合深度学习聚类分割和形态学的混凝土表面裂缝量化识别[J]. 激光与光电子学进展, 2020, 57(22):242-252. 10.3788/lop57.221023 |
YANG J W, ZHANG G, CHEN X J, et al. Quantitative identification of concrete surface cracks based on deep learning clustering segmentation and morphology[J]. Laser and Optoelectronics Progress, 2020, 57(22):242-252 . 10.3788/lop57.221023 | |
37 | XIE Y, LIN B Q, QU Y Y, et al. Joint deep multi-view learning for image clustering[J]. IEEE Transactions on Knowledge and Data Engineering, 2021, 33(11): 3594-3606. 10.1109/tkde.2020.2973981 |
38 | 杨焰飞,曹阳. 基于深度学习的无人机拍摄图像绝缘子目标检测[J]. 激光杂志, 2020, 41(10):63-66. 10.1117/12.2604528 |
YANG Y F, CAO Y. Image insulator target detection based on deep learning for UAV[J]. Laser Journal, 2020, 41(10): 63-66. 10.1117/12.2604528 | |
39 | 高蕴梅. MGTL-SAE精细特征学习的图像资源快速检索[J]. 情报资料工作, 2020, 41(5):79-87. |
GAO Y M. Quick retrieval of image resources based on MGTL-SAE fine feature learning[J]. Information and Documentation Services, 2020, 41(5): 79-87. | |
40 | 闫贺,黄佳,李睿安,等. 基于改进快速区域卷积神经网络的视频SAR运动目标检测算法研究[J]. 电子与信息学报, 2021, 43(3):615-622. 10.11999/JEIT200630 |
YAN H, HUANG J, LI R A, et al. Research on video SAR moving target detection algorithm based on improved Faster Region-based CNN[J]. Journal of Electronics and Information Technology, 2021, 43(3): 615-622. 10.11999/JEIT200630 | |
41 | 杨剑锋,秦钟,庞小龙,等. 基于深度学习网络的输电线路异物入侵监测和识别方法[J]. 电力系统保护与控制, 2021, 49(4):37-44. |
YANG J F, QIN Z, PANG X L, et al. Foreign body intrusion monitoring and recognition method based on Dense-YOLOv3 deep learning network[J]. Power System Protection and Control, 2021, 49(4): 37-44. | |
42 | 陈珂,叶颖雅,马乙平,等. 用于微博情感分析的深度学习网络模型[J]. 计算机与数字工程, 2020, 48(7):1674-1681. |
CHEN K, YE Y Y, MA Y P, et al. Deep learning network model for micro-blog sentiment analysis[J]. Computer and Digital Engineering, 2020, 48(7): 1674-1681. | |
43 | 李艳红,赵宏伟,王素格,等. 面向微博文本流的负面情感突发话题检测[J]. 计算机应用, 2020, 40(12):3458-3464. 10.11772/j.issn.1001-9081.2020060880 |
LI Y H, ZHAO H W, WANG S G, et al. Detection of negative emotion burst topic in microblog text stream[J] Journal of Computer Applications, 2020, 40(12): 3458-3464. 10.11772/j.issn.1001-9081.2020060880 | |
44 | 桑凯恒,张繁昌,李传辉. 地震倒谱特征参数谱聚类地震相分析方法[J]. 石油地球物理勘探, 2021, 56(1):38-48. |
SANG K H, ZHANG F C, LI C H. Seismic facies analysis based on cepstrum characteristic parameters and spectral clustering[J]. Oil Geophysical Prospecting, 2021, 56(1): 38-48. | |
45 | 钱胜胜,张天柱,徐常胜. 多媒体社会事件分析综述[J]. 计算机科学, 2021, 48(3):97-112. 10.11896/jsjkx.210200023 |
QIAN S S, ZHANG T Z, XU C S. Survey of multimedia social events analysis[J]. Computer Science, 2021, 48(3): 97-112. 10.11896/jsjkx.210200023 | |
46 | 王鑫芸,王昊,邓三鸿,等. 面向期刊选择的学术论文内容分类研究[J]. 数据分析与知识发现, 2020, 4(7):96-109. |
WANG X Y, WANG H, DENG S H, et al. Classification of academic papers for periodical selection[J]. Data Analysis and Knowledge Discovery, 2020, 4(7): 96-109. | |
47 | 周晓东,陈人楷,孙华星,等. 基于注意力机制的单通道双人语音分离研究[J]. 通信技术, 2020, 53(4):880-884. 10.3969/j.issn.1002-0802.2020.04.014 |
ZHOU X D, CHEN R K, SUN H X, et al. Single channel dual voice separation based on attention mechanism[J]. Communications Technology, 2020, 53(4): 880-884. 10.3969/j.issn.1002-0802.2020.04.014 | |
48 | WANG Z Q, LE ROUX J, HERSHEY J R. Multi-channel deep clustering: discriminative spectral and spatial embeddings for speaker-independent speech separation[C]// Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2018:1-5. 10.1109/icassp.2018.8461639 |
49 | 杨子民,彭小圣,郎建勋,等. 基于集群动态划分与BLSTM深度学习的风电集群短期功率预测[J]. 高电压技术, 2021, 47(4):1195-1203. |
YANG Z M, PENG X S, LANG J X, et al. Short-term wind power prediction based on dynamic cluster division and BLSTM deep learning method[J]. High Voltage Engineering, 2021, 47(4):1195-1203. | |
50 | 周楠,徐潇源,严正,等. 基于宽度学习系统的光伏发电功率超短期预测[J]. 电力系统自动化, 2021, 45(1):55-64. |
ZHOU N, XU X Y, YAN Z, et al. Ultra-short-term forecasting of photovoltaic power generation based on broad learning system[J]. Automation of Electric Power Systems, 2021, 45(1):55-64. | |
51 | 毛其超,贾瑞生,左羚群,等. 基于深度学习的交通监控视频车辆检测算法[J]. 计算机应用与软件, 2020, 37(9):111-117, 164. 10.3969/j.issn.1000-386x.2020.09.019 |
MAO Q C, JIA R S, ZUO L Q, et al. A traffic surveillance video vehicle detection method based on deep learning[J]. Computer Applications and Software, 2020, 37(9): 111-117, 164. 10.3969/j.issn.1000-386x.2020.09.019 | |
52 | 李亚芳,梁烨,冯韦玮,等. 基于社区优化的深度网络嵌入方法[J]. 计算机应用, 2021, 41(7): 1956-1963. 10.1016/j.jnca.2020.102854 |
LI Y F, LIANG Y, FENG W W, et al. Deep network embedding method based on community optimization[J]. Journal of Computer Applications, 2021, 41(7): 1956-1963. 10.1016/j.jnca.2020.102854 | |
53 | 邱亚星,王希栋,边森,等. 基于聚类分析和深度学习的多频多模网络负载均衡优化[J]. 电信科学, 2020, 36(7): 156-162. |
QIU Y X, WANG X D, BIAN S, et al. Load balancing based on clustering analysis and deep learning for multi-frequency and multi-mode network[J]. Telecommunications Science, 2020, 36(7): 156-162. |
[1] | 王颖洁, 朱久祺, 汪祖民, 白凤波, 弓箭. 自然语言处理在文本情感分析领域应用综述[J]. 《计算机应用》唯一官方网站, 2022, 42(4): 1011-1020. |
[2] | 于婉莹, 梁美玉, 王笑笑, 陈徵, 曹晓雯. 基于深度注意力网络的课堂教学视频中学生表情识别与智能教学评估[J]. 《计算机应用》唯一官方网站, 2022, 42(3): 743-749. |
[3] | 李讷, 徐光柱, 雷帮军, 马国亮, 石勇涛. 交通道路行驶车辆车标识别算法[J]. 《计算机应用》唯一官方网站, 2022, 42(3): 810-817. |
[4] | 危德健, 王文明, 王全玉, 任好盼, 高彦彦, 王志. 改进的基于锚点的三维手部姿态估计网络[J]. 《计算机应用》唯一官方网站, 2022, 42(3): 953-959. |
[5] | 陈亭秀, 尹建芹. 基于关键帧筛选网络的视听联合动作识别[J]. 《计算机应用》唯一官方网站, 2022, 42(3): 731-735. |
[6] | 孙邱杰, 梁景贵, 李思. 基于BART噪声器的中文语法纠错模型[J]. 《计算机应用》唯一官方网站, 2022, 42(3): 860-866. |
[7] | 刘海杨, 孟令航, 林仲航, 谷源涛. 基于轨迹点聚类的航路发现方法[J]. 《计算机应用》唯一官方网站, 2022, 42(3): 890-894. |
[8] | 陈育丹, 高翠芳, 沈莞蔷, 殷萍. 迭代直觉模糊K-modes算法[J]. 《计算机应用》唯一官方网站, 2022, 42(2): 375-381. |
[9] | 高苏, 鲍君忠, 王昕, 王利东. 可解释性有序聚类方法及其应用分析[J]. 《计算机应用》唯一官方网站, 2022, 42(2): 457-462. |
[10] | 曹建荣, 朱亚琴, 张玉婷, 吕俊杰, 杨红娟. 基于关节点特征的跌倒检测算法[J]. 《计算机应用》唯一官方网站, 2022, 42(2): 622-630. |
[11] | 陈薪羽, 刘明哲, 任俊, 汤影. 基于多列卷积神经网络的参数异步更新算法[J]. 《计算机应用》唯一官方网站, 2022, 42(2): 395-403. |
[12] | 高磊, 罗关凤, 刘荡, 闵帆. 基于聚类和局部线性回归的初至波自动拾取算法[J]. 《计算机应用》唯一官方网站, 2022, 42(2): 655-662. |
[13] | 李俊伯, 秦品乐, 曾建潮, 李萌. 基于超分辨率网络的CT三维重建算法[J]. 《计算机应用》唯一官方网站, 2022, 42(2): 584-591. |
[14] | 彭宇, 李晓瑜, 胡世杰, 刘晓磊, 钱伟中. 基于BERT的三阶段式问答模型[J]. 《计算机应用》唯一官方网站, 2022, 42(1): 64-70. |
[15] | 马敬奇, 雷欢, 陈敏翼. 基于AlphaPose优化模型的老人跌倒行为检测算法[J]. 《计算机应用》唯一官方网站, 2022, 42(1): 294-301. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||