{"type":"ScholarlyArticle","title":"Three-Player Wasserstein GAN via Amortised Duality","authors":[{"name":"Nhan Dam","slug":"nhan-dam","given":"Nhan","family":"Dam","affiliation":"Monash University"},{"name":"Quan Hoang","slug":"quan-hoang","given":"Quan","family":"Hoang","affiliation":"Monash University"},{"name":"Trung Le","slug":"trung-le","given":"Trung","family":"Le","affiliation":"Monash University"},{"name":"Tu Dinh Nguyen","slug":"tu-dinh-nguyen","given":"Tu Dinh","family":"Nguyen","affiliation":"Monash University"},{"name":"Hung Bui","slug":"hung-bui","given":"Hung","family":"Bui","affiliation":"Google DeepMind"},{"name":"Dinh Phung","slug":"dinh-phung","given":"Dinh","family":"Phung","affiliation":"Monash University"}],"abstract":"We propose a new formulation for learning generative adversarial networks (GANs) using optimal transport cost (the general form of Wasserstein distance) as the objective criterion to measure the dissimilarity between target distribution and learned distribution. Our formulation is based on the general form of the Kantorovich duality which is applicable to optimal transport with a wide range of cost functions that are not necessarily metric. To make optimising this duality form amenable to gradient-based methods, we employ a function that acts as an amortised optimiser for the innermost optimisation problem. Interestingly, the amortised optimiser can be viewed as a mover since it strategically shifts around data points. The resulting formulation is a sequential min-max-min game with 3 players: the generator, the critic, and the mover where the new player, the mover, attempts to fool the critic by shifting the data around. Despite involving three players, we demonstrate that our proposed formulation can be trained reasonably effectively via a simple alternative gradient learning strategy. Compared with the existing Lipschitz-constrained formulations of Wasserstein GAN on CIFAR-10, our model yields significantly better diversity scores than weight clipping and comparable performance to gradient penalty method.","doi":"10.24963/ijcai.2019/305","url":"https://ijcai.org/proceedings/2019/305","pdf":"https://ijcai.org/proceedings/2019/0305.pdf","markdown":"https://ijcai.org/proceedings/2019/305.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/305","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 A-L","track":"Main track","number":305,"pages":{"first":2202,"last":2208},"keywords":["Machine Learning: Deep Learning","Machine Learning: Unsupervised Learning","Machine Learning: Learning Generative Models"],"videos":[],"references":[{"position":1,"raw":"[Abadi et al., 2016] Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, et al. Tensorflow: Large-scale machine learn- ing on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467, 2016.","title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems","authors":"Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Arjovsky et al., 2017] Martin Arjovsky, Soumith Chintala, and Léon Bottou. Wasserstein generative adversarial net- works. In International Conference on Machine Learning, pages 214-223, 2017.","title":"Wasserstein generative adversarial networks","authors":"Martin Arjovsky, Soumith Chintala, Léon Bottou","year":"2017","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Dziugaite et al., 2015] Gintare Karolina Dziugaite, Daniel M. Roy, and Zoubin Ghahramani. Training generative neural networks via maximum mean discrep- ancy optimization. In Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence, UAI'15, pages 258-267, Arlington, Virginia, United States, 2015. AUAI Press.","title":"Training generative neural networks via maximum mean discrepancy optimization","authors":"Gintare Karolina Dziugaite, Daniel M Roy, Zoubin Ghahramani","year":"2015","venue":"Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence, UAI'15","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Goodfellow et al., 2014] Ian Goodfellow, Jean Pouget- Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Gen- erative adversarial nets. In Advances in neural information processing systems, pages 2672-2680, 2014.","title":"Generative adversarial nets","authors":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio","year":"2014","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Goodfellow, 2016] Ian Goodfellow. Nips 2016 tuto- rial: Generative adversarial networks. arXiv preprint arXiv:1701.00160, 2016.","title":"Nips 2016 tutorial: Generative adversarial networks","authors":"Ian Goodfellow","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Gulrajani et al., 2017] Ishaan Gulrajani, Faruk Ahmed, Martin Arjovsky, Vincent Dumoulin, and Aaron C Courville. Improved training of wasserstein gans. In Ad- vances in Neural Information Processing Systems, pages 5769-5779, 2017.","title":"Improved training of wasserstein gans","authors":"Ishaan Gulrajani, Faruk Ahmed, Martin Arjovsky, Aaron C Vincent Dumoulin, Courville","year":"2017","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Heusel et al., 2017] Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochre- iter. Gans trained by a two time-scale update rule converge to a local nash equilibrium. In Advances in Neu- ral Information Processing Systems, pages 6629-6640, 2017.","title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","authors":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, Sepp Hochreiter","year":"2017","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hoang et al., 2018] Quan Hoang, Tu Dinh Nguyen, Trung Le, and Dinh Phung. MGAN: Training generative adver- sarial nets with multiple generators. In International Con- ference on Learning Representations, 2018.","title":"MGAN: Training generative adversarial nets with multiple generators","authors":"Quan Hoang, Tu Dinh Nguyen, Trung Le, Dinh Phung","year":"2018","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kingma and Ba, 2014] Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Krizhevsky and Hinton, 2009] Alex Krizhevsky and Geof- frey Hinton. Learning multiple layers of features from tiny images. 2009.","title":"Learning multiple layers of features from tiny images","authors":"Alex Krizhevsky, Geoffrey Hinton","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Le et al., 2018] Trung Le, Hung Vu, Tu Dinh Nguyen, and Dinh Phung. Geometric enclosing networks. In Proceed- ings of the 27th International Joint Conference on Artifi- cial Intelligence, pages 2355-2361. AAAI Press, 2018.","title":"Geometric enclosing networks","authors":"Trung Le, Hung Vu, Tu Dinh Nguyen, Dinh Phung","year":"2018","venue":"Proceedings of the 27th International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2018/326"},{"position":12,"raw":"[Le et al., 2019] Trung Le, Quan Hoang, Hung Vu, Tu Dinh Nguyen, Hung Bui, and Dinh Phung. Learning genera- tive adversarial networks from multiple data sources. In Proceedings of the 28th International Joint Conference on Artificial Intelligence, 2019.","title":"Learning generative adversarial networks from multiple data sources","authors":"Trung Le, Quan Hoang, Hung Vu, Tu Dinh Nguyen, Hung Bui, Dinh Phung","year":"2019","venue":"Proceedings of the 28th International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2019/391"},{"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 the IEEE International Conference on Computer Vision, pages 3730-3738, 2015.","title":"Deep learning face attributes in the wild","authors":"Ziwei Liu, Ping Luo, Xiaogang Wang, Xiaoou Tang","year":"2015","venue":"Proceedings of the IEEE International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Miyato et al., 2018] Takeru Miyato, Toshiki Kataoka, Masanori Koyama, and Yuichi Yoshida. Spectral normal- ization for generative adversarial networks. International Conference on Learning Representations, 2018.","title":"Spectral normalization for generative adversarial networks","authors":"Miyato","year":"2018","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Nguyen et al., 2017] Tu Nguyen, Trung Le, Hung Vu, and Dinh Phung. Dual discriminator generative adversarial nets. In Advances in Neural Information Processing Sys- tems, pages 2670-2680, 2017.","title":"Dual discriminator generative adversarial nets","authors":"Tu Nguyen, Trung Le, Hung Vu, Dinh Phung","year":"2017","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Nowozin et al., 2016] Sebastian Nowozin, Botond Cseke, and Ryota Tomioka. f-gan: Training generative neu- ral samplers using variational divergence minimization. In Advances in Neural Information Processing Systems, 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","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Radford et al., 2015] Alec Radford, Luke Metz, and Soumith Chintala. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434, 2015.","title":"Unsupervised representation learning with deep convolutional generative adversarial networks","authors":"Radford","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Salimans et al., 2016] Tim Salimans, Ian Goodfellow, Woj- ciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen. Improved techniques for training gans. In Advances in Neural Information Processing Systems, pages 2234- 2242, 2016.","title":"Improved techniques for training gans","authors":"Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, Xi Chen","year":"2016","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Santambrogio, 2015] Filippo Santambrogio. Optimal Transport for Applied Mathematicians: Calculus of Varia- tions, PDEs, and Modeling, volume 87. Birkhäuser, 2015.","title":"Optimal Transport for Applied Mathematicians: Calculus of Variations","authors":"Filippo Santambrogio","year":"2015","venue":"PDEs, and Modeling","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Villani, 2008] Cédric Villani. Optimal transport: old and new, volume 338. Springer Science & Business Media, 2008.","title":"Optimal transport: old and new","authors":"Villani","year":"2008","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Wei et al., 2018] Xiang Wei, Boqing Gong, Zixia Liu, Wei Lu, and Liqiang Wang. Improving the improved training of wasserstein gans: A consistency term and its dual effect. arXiv preprint arXiv:1803.01541, 2018.","title":"Improving the improved training of wasserstein gans: A consistency term and its dual effect","authors":"Xiang Wei, Boqing Gong, Zixia Liu, Wei Lu, Liqiang Wang","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wu et al., 2016] Jiajun Wu, Chengkai Zhang, Tianfan Xue, Bill Freeman, and Josh Tenenbaum. Learning a proba- bilistic latent space of object shapes via 3d generative- adversarial modeling. In Advances in Neural Information Processing Systems, pages 82-90, 2016.","title":"Learning a probabilistic latent space of object shapes via 3d generativeadversarial modeling","authors":"Jiajun Wu, Chengkai Zhang, Tianfan Xue, Bill Freeman, Josh Tenenbaum","year":"2016","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Zhang et al., 2016] Han Zhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaolei Huang, Xiaogang Wang, and Dimitris Metaxas. Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks. arXiv preprint arXiv:1612.03242, 2016.","title":"Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks","authors":"Han Zhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaolei Huang, Xiaogang Wang, Dimitris Metaxas","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Zhu et al., 2017] Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A Efros. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceed- ings of the IEEE International Conference on Computer Vision, pages 2223-2232, 2017.","title":"Unpaired image-to-image translation using cycle-consistent adversarial networks","authors":"Zhu","year":"2017","venue":"Proceedings of the IEEE International Conference on Computer Vision","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}