{"type":"ScholarlyArticle","title":"GAN-EM: GAN Based EM Learning Framework","authors":[{"name":"Wentian Zhao","slug":"wentian-zhao","given":"Wentian","family":"Zhao","affiliation":"University of Rochester"},{"name":"Shaojie Wang","slug":"shaojie-wang","given":"Shaojie","family":"Wang","affiliation":"University of Rochester"},{"name":"Zhihuai Xie","slug":"zhihuai-xie","given":"Zhihuai","family":"Xie","affiliation":"Tsinghua University"},{"name":"Jing Shi","slug":"jing-shi","given":"Jing","family":"Shi","affiliation":"University of Rochester"},{"name":"Chenliang Xu","slug":"chenliang-xu","given":"Chenliang","family":"Xu","affiliation":"University of Rochester"}],"abstract":"Expectation maximization (EM) algorithm is to find maximum likelihood solution for models having latent variables. A typical example is Gaussian Mixture Model (GMM) which requires Gaussian assumption, however, natural images are highly non-Gaussian so that GMM cannot be applied to perform image clustering task on pixel space. To overcome such limitation, we propose a GAN based EM learning framework that can maximize the likelihood of images and estimate the latent variables. We call this model GAN-EM, which is a framework for image clustering, semi-supervised classification and dimensionality reduction. In M-step, we design a novel loss function for discriminator of GAN to perform maximum likelihood estimation (MLE) on data with soft class label assignments. Specifically, a conditional generator captures data distribution for K classes, and a discriminator tells whether a sample is real or fake for each class. Since our model is unsupervised, the class label of real data is regarded as latent variable, which is estimated by an additional network (E-net) in E-step. The proposed GAN-EM achieves state-of-the-art clustering and semi-supervised classification results on MNIST, SVHN and CelebA, as well as comparable quality of generated images to other recently developed generative models.","doi":"10.24963/ijcai.2019/612","url":"https://ijcai.org/proceedings/2019/612","pdf":"https://ijcai.org/proceedings/2019/0612.pdf","markdown":"https://ijcai.org/proceedings/2019/612.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/612","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Machine Learning M-Z","track":"Main track","number":612,"pages":{"first":4404,"last":4411},"keywords":["Machine Learning: Clustering","Machine Learning: Learning Generative Models"],"videos":[],"references":[{"position":1,"raw":"[Banijamali et al., 2017] Ershad Banijamali, Ali Ghodsi, and Pascal Poupart. Generative mixture of networks. In 2017 International Joint Conference on Neural Networks, IJCNN 2017, Anchorage, AK, USA, May 14-19, 2017, pages 3753-3760, 2017.","title":"Generative mixture of networks","authors":"Ershad Banijamali, Ali Ghodsi, Pascal Poupart","year":"2017","venue":"2017 International Joint Conference on Neural Networks, IJCNN 2017","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bishop, 2006] Christopher M. Bishop. Pattern Recognition and Machine Learning (Information Science and Statis- tics). Springer-Verlag, Berlin, Heidelberg, 2006.","title":"Pattern Recognition and Machine Learning (Information Science and Statistics)","authors":"Christopher M Bishop","year":"2006","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Dagher and Nachar, 2006] Issam Dagher and Rabih Nachar. Face recognition using IPCA-ICA algorithm. IEEE Trans. Pattern Anal. Mach. Intell., 28(6):996-1000, 2006.","title":"Face recognition using IPCA-ICA algorithm","authors":"Issam Dagher, Rabih Nachar","year":"2006","venue":"IEEE Trans. Pattern Anal. Mach. Intell","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Dempster et al., 1977] A. P. Dempster, N. M. Laird, and D. B. Rubin. Maximum likelihood from incomplete data via the em algorithm. Journal of the Royal Statistical So- ciety. Series B (Methodological), 39(1):1-38, 1977.","title":"Maximum likelihood from incomplete data via the em algorithm","authors":"A P Dempster, N M Laird, D B Rubin","year":"1977","venue":"Journal of the Royal Statistical Society. Series B (Methodological)","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Donahue et al., 2016] Jeff Donahue, Philipp Krähenbühl, and Trevor Darrell. Adversarial feature learning. CoRR, abs/1605.09782, 2016.","title":"Adversarial feature learning","authors":"Jeff Donahue, Philipp Krähenbühl, Trevor Darrell","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Goodfellow et al., 2014] Ian J. Goodfellow, Jean Pouget- Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron C. Courville, and Yoshua Bengio. Generative adversarial nets. In Advances in Neural In- formation Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, December 8-13 2014, Montreal, Quebec, Canada, pages 2672-2680, 2014.","title":"Generative adversarial nets","authors":"Ian J Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron C Courville, Yoshua Bengio","year":"2014","venue":"Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Goodfellow, 2017] Ian J. Goodfellow. NIPS 2016 tutorial: Generative adversarial networks. CoRR, abs/1701.00160, 2017.","title":"NIPS 2016 tutorial: Generative adversarial networks","authors":"Ian J Goodfellow","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Greff et al., 2017] Klaus Greff, Sjoerd van Steenkiste, and Jürgen Schmidhuber. Neural expectation maximization. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Sys- tems 2017, 4-9 December 2017, Long Beach, CA, USA, pages 6694-6704, 2017.","title":"Neural expectation maximization","authors":"Greff","year":"2017","venue":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hinton, 2008] G. E. Hinton. Visualizing high-dimensional data using t-sne. Journal of Machine Learning Research, 9(2):2579-2605, 2008.","title":"Visualizing high-dimensional data using t-sne","authors":"G E Hinton","year":"2008","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Jiang et al., 2017] Zhuxi Jiang, Yin Zheng, Huachun Tan, Bangsheng Tang, and Hanning Zhou. Variational deep embedding: An unsupervised and generative approach to clustering. In Proceedings of the Twenty-Sixth Interna- tional Joint Conference on Artificial Intelligence, IJCAI, Melbourne, Australia, pages 1965-1972, 2017.","title":"Variational deep embedding: An unsupervised and generative approach to clustering","authors":"Jiang","year":"2017","venue":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2017/273"},{"position":11,"raw":"[Krizhevsky et al., 2012] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems 25: 26th Annual Con- ference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012, Lake Tahoe, Nevada, United States., pages 1106-1114, 2012.","title":"Imagenet classification with deep convolutional neural networks","authors":"Alex Krizhevsky, Ilya Sutskever, Geoffrey E Hinton","year":"2012","venue":"Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[LeCun et al., 1989] Yann LeCun, Bernhard E. Boser, John S. Denker, Donnie Henderson, Richard E. Howard, Wayne E. Hubbard, and Lawrence D. Jackel. Backpropa- gation applied to handwritten zip code recognition. Neural Computation, 1(4):541-551, 1989.","title":"Backpropagation applied to handwritten zip code recognition","authors":"Yann Lecun, Bernhard E Boser, John S Denker, Donnie Henderson, Richard E Howard, Wayne E Hubbard, Lawrence D Jackel","year":"1989","venue":"Neural Computation","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Liu et al., 2015] Ziwei Liu, Ping Luo, Xiaogang Wang, and Xiaoou Tang. Deep learning face attributes in the wild. In Proceedings of International Conference on Computer Vision (ICCV), 2015.","title":"Deep learning face attributes in the wild","authors":"Ziwei Liu, Ping Luo, Xiaogang Wang, Xiaoou Tang","year":"2015","venue":"Proceedings of International Conference on Computer Vision (ICCV)","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Makhzani and Frey, 2017] Alireza Makhzani and Bren- dan J. Frey. Pixelgan autoencoders. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4-9 De- cember 2017, Long Beach, CA, USA, pages 1972-1982, 2017.","title":"Pixelgan autoencoders","authors":"Alireza Makhzani, Brendan J Frey","year":"2017","venue":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Makhzani et al., 2015] Alireza Makhzani, Jonathon Shlens, Navdeep Jaitly, and Ian J. Goodfellow. Adversarial au- toencoders. CoRR, abs/1511.05644, 2015.","title":"Adversarial autoencoders","authors":"Alireza Makhzani, Jonathon Shlens, Navdeep Jaitly, Ian J Goodfellow","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Mirza and Osindero, 2014] Mehdi Mirza and Simon Osin- dero. Conditional generative adversarial nets. CoRR, abs/1411.1784, 2014.","title":"Conditional generative adversarial nets","authors":"Mehdi Mirza, Simon Osindero","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Netzer et al., 2011] Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, and Andrew Y. Ng. Reading digits in natural images with unsupervised feature learn- ing. NIPS Workshop on Deep Learning and Unsupervised Feature Learning, 2011.","title":"Reading digits in natural images with unsupervised feature learning","authors":"Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, Andrew Y Ng","year":"2011","venue":"NIPS Workshop on Deep Learning and Unsupervised Feature Learning","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Nowozin et al., 2016] Sebastian Nowozin, Botond Cseke, and Ryota Tomioka. f-gan: Training generative neural samplers using variational divergence minimization. In Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Sys- tems 2016, December 5-10, 2016, Barcelona, Spain, pages 271-279, 2016.","title":"f-gan: Training generative neural samplers using variational divergence minimization","authors":"Sebastian Nowozin, Botond Cseke, Ryota Tomioka","year":"2016","venue":"Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Peng et al., 2016] Xi Peng, Shijie Xiao, Jiashi Feng, Wei- Yun Yau, and Zhang Yi. Deep subspace clustering with sparsity prior. In IJCAI, pages 1925-1931. IJCAI/AAAI Press, 2016.","title":"Deep subspace clustering with sparsity prior","authors":"Xi Peng, Shijie Xiao, Jiashi Feng, Wei-Yun Yau, Zhang Yi","year":"2016","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2016/275"},{"position":20,"raw":"[Salimans et al., 2016] Tim Salimans, Ian J. Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen. Improved techniques for training gans. In Ad- vances in Neural Information Processing Systems 29: An- nual Conference on Neural Information Processing Sys- tems 2016, December 5-10, 2016, Barcelona, Spain, pages 2226-2234, 2016.","title":"Improved techniques for training gans","authors":"Tim Salimans, Ian J Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, Xi Chen","year":"2016","venue":"Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Springenberg, 2015] Jost Tobias Springenberg. Unsuper- vised and semi-supervised learning with categorical gener- ative adversarial networks. CoRR, abs/1511.06390, 2015.","title":"Unsupervised and semi-supervised learning with categorical generative adversarial networks","authors":"Jost Tobias, Springenberg","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Spurr et al., 2017] Adrian Spurr, Emre Aksan, and Otmar Hilliges. Guiding infogan with semi-supervision. In Ma- chine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2017, Skopje, Mace- donia, September 18-22, 2017, Proceedings, Part I, pages 119-134, 2017.","title":"Guiding infogan with semi-supervision","authors":"Adrian Spurr, Emre Aksan, Otmar Hilliges","year":"2017","venue":"Machine Learning and Knowledge Discovery in Databases -European Conference, ECML PKDD 2017","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Srivastava et al., 2003] A. Srivastava, A. B. Lee, Eero P. Si- moncelli, and S.-C. Zhu. On advances in statistical mod- eling of natural images. Journal of Mathematical Imaging and Vision, 18(1):17-33, 2003.","title":"On advances in statistical modeling of natural images","authors":"A Srivastava, A B Lee, Eero P Simoncelli, S.-C Zhu","year":"2003","venue":"Journal of Mathematical Imaging and Vision","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wainwright and Simoncelli, 1999] Martin J. Wainwright and Eero P. Simoncelli. Scale mixtures of gaussians and the statistics of natural images. In NIPS, pages 855-861. The MIT Press, 1999.","title":"Scale mixtures of gaussians and the statistics of natural images","authors":"Martin J Wainwright, Eero P Simoncelli","year":"1999","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Xie et al., 2016] Junyuan Xie, Ross B. Girshick, and Ali Farhadi. Unsupervised deep embedding for clustering analysis. In Proceedings of the 33nd International Con- ference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016, pages 478-487, 2016.","title":"Unsupervised deep embedding for clustering analysis","authors":"Junyuan Xie, Ross B Girshick, Ali Farhadi","year":"2016","venue":"Proceedings of the 33nd International Conference on Machine Learning, ICML 2016","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Yang and Zhou, 2018] Yu Yang and Wen-Ji Zhou. Mix- ture of gans for clustering. In Proceedings of the Twenty- Seventh International Joint Conference on Artificial Intel- ligence, IJCAI, Stockholm, Sweden, 2018.","title":"Mixture of gans for clustering","authors":"Yu Yang, Wen-Ji Zhou","year":"2018","venue":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2018/423"}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}