Abstract
This paper presents a novel clustering approach that utilizes variational autoencoders (VAEs) with disentangled representations, enhancing the efficiency and effectiveness of clustering. Traditional VAE-based clustering models often conflate generative and clustering information, leading to suboptimal clustering performance. To overcome this, our model distinctly separates latent representations into two modules: one for clustering and another for generation. This separation significantly improves clustering performance. Additionally, we employ augmented data to maximize mutual information between cluster assignment variables and the optimized latent variables. This strategy not only enhances clustering effectiveness but also allows the construction of latent variables that synergistically combine clustering information from original data with generative information from augmented data. Through extensive experiments, our model demonstrates superior clustering performance without the need for pre-training, outperforming existing deep generative clustering models. Moreover, it achieves state-of-the-art clustering accuracy on certain datasets, surpassing models that require pre-training.
Similar content being viewed by others
Data Availability
The MNIST data sets is available at: [http://yann.lecun.com/exdb/mnist/]. The USPS data set is available at: [https://www.kaggle.com/datasets/bistaumanga/usps-dataset]. The GTSRB data set is available at: [https://benchmark.ini.rub.de/gtsrb_news.html] The YTF data set is available at: [https://www.cs.tau.ac.il/~wolf/ytfaces/] The F-MNIST data set is available at: [https://www.kaggle.com/datasets/zalando-research/fashionmnist].
References
Cai J, Wang S, Guo W (2021) Unsupervised embedded feature learning for deep clustering with stacked sparse auto-encoder. Expert Syst Appl 186(115):729
Cao L, Asadi S, Zhu W, Schmidli C, Sjöberg M (2020) Simple, scalable, and stable variational deep clustering. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp 108–124
Chen RT, Li X, Grosse RB, Duvenaud DK (2018) Isolating sources of disentanglement in variational autoencoders. vol 31
Chen X, Duan Y, Houthooft R, Schulman J, Sutskever I, Abbeel P (2016) Infogan: Interpretable representation learning by information maximizing generative adversarial nets. In: Advances in neural information processing systems, vol 29
Dai Q, Zhao C, Zhao S (2022) Variational bayesian student’st mixture model with closed-form missing value imputation for robust process monitoring of low-quality data. IEEE Trans Cybern pp 1–14
Diallo B, Hu J, Li T, Khan GA, Liang X, Zhao Y (2021) Deep embedding clustering based on contractive autoencoder. Neurocomputing 433:96–107
Dilokthanakul N, Mediano PA, Garnelo M, Lee MC, Salimbeni H, Arulkumaran K, Shanahan M (2016) Deep unsupervised clustering with gaussian mixture variational autoencoders. arXiv preprint arXiv:1611.02648
Dupont E (2018) Learning disentangled joint continuous and discrete representations. vol 31
Fan W, Bouguila N (2014) Variational learning for dirichlet process mixtures of dirichlet distributions and applications. Multimed Tools Appl 70(3):1685–1702
Fan W, Hou W (2022) Unsupervised modeling and feature selection of sequential spherical data through nonparametric hidden markov models. Int J Mach Learn Cybern 13(10):3019–3029
Fan W, Sallay H, Bouguila N, Bourouis S (2016) Variational learning of hierarchical infinite generalized dirichlet mixture models and applications. Soft Comput 20(3):979–990
Fan W, Bouguila N, Bourouis S, Laalaoui Y (2018) Entropy-based variational bayes learning framework for data clustering. IET Image Proc 12(10):1762–1772
Fan W, Bouguila N, Du JX, Liu X (2019) Axially symmetric data clustering through dirichlet process mixture models of watson distributions. IEEE Trans Neural Netw Learn Syst 30(6):1683–1694
Fan W, Yang L, Bouguila N (2022) Unsupervised grouped axial data modeling via hierarchical bayesian nonparametric models with watson distributions. IEEE Trans Pattern Anal Mach Intell 44(12):9654–9668
Fan W, Zeng L, Wang T (2023) Uncertainty quantification in molecular property prediction through spherical mixture density networks. Eng Appl Artif Intell 123(106):180
Fei Z, Gong H, Guo J, Wang J, Jin W, Xiang X, Ding X, Zhang N (2023) Image clustering: Utilizing teacher-student model and autoencoder. IEEE Access 11:104,846-104,857
Feng K, Qin H, Wu S, Pan W, Liu G (2020) A sleep apnea detection method based on unsupervised feature learning and single-lead electrocardiogram. IEEE Trans Instrum Meas 70:1–12
Gao X, Huang W, Liu Y, Zhang Y, Zhang J, Li C, Bore JC, Wang Z, Si Y, Tian Y et al (2023) A novel robust student’s t-based granger causality for eeg based brain network analysis. Biomed Signal Process Control 80(104):321
Ge P, Ren CX, Dai DQ, Feng J, Yan S (2019) Dual adversarial autoencoders for clustering. IEEE Trans Neural Netw Learn Syst 31(4):1417–1424
Ghasedi Dizaji K, Herandi A, Deng C, Cai W, Huang H (2017) Deep clustering via joint convolutional autoencoder embedding and relative entropy minimization. In: Proceedings of the IEEE international conference on computer vision, pp 5736–5745
Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville AC, Bengio Y (2014) Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol 27
Guo X, Gao L, Liu X, Yin J (2017a) Improved deep embedded clustering with local structure preservation. In: Ijcai, pp 1753–1759
Guo X, Liu X, Zhu E, Yin J (2017b) Deep clustering with convolutional autoencoders. In: International conference on neural information processing, pp 373–382
Haeusser P, Plapp J, Golkov V, Aljalbout E, Cremers D (2019) Associative deep clustering: Training a classification network with no labels. In: Pattern Recognition: 40th German Conference, GCPR 2018, Stuttgart, Germany, October 9-12, 2018, Proceedings 40, pp 18–32
Higgins I, Matthey L, Pal A, Burgess C, Glorot X, Botvinick M, Mohamed S, Lerchner A (2017) beta-vae: Learning basic visual concepts with a constrained variational framework. In: International conference on learning representations
Houben S, Stallkamp J, Salmen J, Schlipsing M, Igel C (2013) Detection of traffic signs in real-world images: The german traffic sign detection benchmark. In: The 2013 international joint conference on neural networks (IJCNN), pp 1–8
Hu Q, Zhang G, Qin Z, Cai Y, Yu G, Li GY (2023) Robust semantic communications with masked vq-vae enabled codebook. IEEE Transactions on Wireless Communications p 1
Ji X, Henriques JF, Vedaldi A (2019) Invariant information clustering for unsupervised image classification and segmentation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 9865–9874
Jiang Z, Zheng Y, Tan H, Tang B, Zhou H (2016) Variational deep embedding: An unsupervised and generative approach to clustering. arXiv preprint arXiv:1611.05148
Kim H, Mnih A (2018) Disentangling by factorising. In: International Conference on Machine Learning, pp 2649–2658
Kingma DP, Welling M (2013) Auto-encoding variational bayes. In: International Conference on Learning Representations
Külah E, Çetinkaya YM, Özer AG, Alemdar H (2023) Covid-19 forecasting using shifted gaussian mixture model with similarity-based estimation. Expert Syst Appl 214(119):034
Le Guennec A, Malinowski S, Tavenard R (2016) Data augmentation for time series classification using convolutional neural networks. In: ECML/PKDD workshop on advanced analytics and learning on temporal data, pp 3558–3565
LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
Li B, Wu F, Weinberger KQ, Belongie S (2019) Positional normalization. vol 32
Li B, Wu F, Lim SN, Belongie S, Weinberger KQ (2021a) On feature normalization and data augmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 12,383–12,392
Li X, Kou K, Zhao B (2021b) Weather gan: Multi-domain weather translation using generative adversarial networks. arXiv preprint arXiv:2103.05422
Liu T, Yuan Q, Ding X, Wang Y, Zhang D (2023) Multi-objective optimization for greenhouse light environment using gaussian mixture model and an improved nsga-ii algorithm. Comput Electron Agric 205(107):612
Liu X, Hu Z, Ling H, Cheung YM (2021) Mtfh: A matrix tri-factorization hashing framework for efficient cross-modal retrieval. IEEE Trans Pattern Anal Mach Intell 43(3):964–981
Lloyd S (1982) Least squares quantization in pcm. IEEE Trans Inf Theory 28(2):129–137
Van der Maaten L, Hinton G (2008) Visualizing data using t-sne. J Mach Learn Res 9(11):2579–2605
Makhzani A, Shlens J, Jaitly N, Goodfellow I, Frey B (2015) Adversarial autoencoders. arXiv preprint arXiv:1511.05644
Marsaglia G, Tsang WW (2000) A simple method for generating gamma variables. ACM Trans Math Softw (TOMS) 26(3):363–372
McLachlan GJ, Lee SX, Rathnayake SI (2019) Finite mixture models. Ann Rev Stat Appl 6:355–378
Meitz M, Preve D, Saikkonen P (2023) A mixture autoregressive model based on student’s t-distribution. Commun Stat Theory Methods 52(2):499–515
Miklautz L, Bauer LG, Mautz D, Tschiatschek S, Böhm C, Plant C (2021) Details (don’t) matter: Isolating cluster information in deep embedded spaces. In: IJCAI, pp 2826–2832
Mukherjee S, Asnani H, Lin E, Kannan S (2019) Clustergan: Latent space clustering in generative adversarial networks. Proc AAAI Conf Artif Intell 33:4610–4617
Naesseth C, Ruiz F, Linderman S, Blei D (2017) Reparameterization gradients through acceptance-rejection sampling algorithms. In: Artificial Intelligence and Statistics, pp 489–498
Niknam G, Molaei S, Zare H, Clifton D, Pan S (2023) Graph representation learning based on deep generative gaussian mixture models. Neurocomputing 523:157–169
Satheesh C, Kamal S, Mujeeb A, Supriya M (2021) Passive sonar target classification using deep generative \(\beta\)-vae. IEEE Signal Process Lett 28:808–812
Sevgen E, Moller J, Lange A, Parker J, Quigley S, Mayer J, Srivastava P, Gayatri S, Hosfield D, Korshunova M, et al (2023) Prot-vae: Protein transformer variational autoencoder for functional protein design. bioRxiv pp 2023–01
Wolf L, Hassner T, Maoz I (2011) Face recognition in unconstrained videos with matched background similarity. CVPR 2011:529–534
Xiao H, Rasul K, Vollgraf R (2017) Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747
Xie J, Girshick R, Farhadi A (2016) Unsupervised deep embedding for clustering analysis. In: International conference on machine learning, pp 478–487
Xu W, Liu X, Gong Y (2003) Document clustering based on non-negative matrix factorization. In: Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval, pp 267–273
Yang B, Fu X, Sidiropoulos ND, Hong M (2017) Towards k-means-friendly spaces: Simultaneous deep learning and clustering. In: International conference on machine learning, pp 3861–3870
Yang L, Fan W, Bouguila N (2022) Clustering analysis via deep generative models with mixture models. IEEE Trans Neural Netw Learn Syst 33(1):340–350
Yang L, Fan W, Bouguila N (2022) Robust unsupervised image categorization based on variational autoencoder with disentangled latent representations. Knowl-Based Syst 246(108):671
Yang L, Fan W, Bouguila N (2023) Deep clustering analysis via dual variational autoencoder with spherical latent embeddings. IEEE Trans Neural Netw Learn Syst 34(9):6303–6312
Yang X, Deng C, Zheng F, Yan J, Liu W (2019) Deep spectral clustering using dual autoencoder network. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 4066–4075
Yang X, Yan J, Cheng Y, Zhang Y (2023) Learning deep generative clustering via mutual information maximization. IEEE Trans Neural Netw Learn Syst 34(9):6263–6275
Zhang Y, Fan W, Bouguila N (2019) Unsupervised image categorization based on variational autoencoder and student’st mixture model. In: 2019 IEEE Symposium Series on Computational Intelligence (SSCI), pp 2403–2409
Zhu X, Zhu Y, Zheng W (2020) Spectral rotation for deep one-step clustering. Pattern Recogn 105(107):175
Zhu X, Xu C, Tao D (2021) Commutative lie group vae for disentanglement learning. In: International Conference on Machine Learning, pp 12,924–12,934
Acknowledgements
The completion of this work was supported by the National Natural Science Foundation of China (62276106), the Guangdong Provincial Key Laboratory IRADS (2022B1212010006, R0400001-22) and the UIC Start-up Research Fund (UICR0700056-23).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Xu, K., Fan, W. & Liu, X. Deep generative clustering methods based on disentangled representations and augmented data. Int. J. Mach. Learn. & Cyber. (2024). https://doi.org/10.1007/s13042-024-02173-9
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s13042-024-02173-9