Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching

A broad range of cross-$m$-domain generation researches boil down to matching a joint distribution by deep generative models (DGMs). Hitherto algorithms excel in pairwise domains while as $m$ increases, remain struggling to scale themselves to fit a joint distribution. In this paper, we propose a domain-scalable DGM, i.e., MMI-ALI for $m$-domain joint distribution matching. As an $m$-domain ensemble model of ALIs \cite{dumoulin2016adversarially}, MMI-ALI is adversarially trained with maximizing Multivariate Mutual Information (MMI) w.r.t. joint variables of each pair of domains and their shared feature. The negative MMIs are upper bounded by a series of feasible losses that provably lead to matching $m$-domain joint distributions. MMI-ALI linearly scales as $m$ increases and thus, strikes a right balance between efficacy and scalability. We evaluate MMI-ALI in diverse challenging $m$-domain scenarios and verify its superiority.

[1]  Trevor Darrell,et al.  Adversarial Feature Learning , 2016, ICLR.

[2]  Valentin Khrulkov,et al.  Geometry Score: A Method For Comparing Generative Adversarial Networks , 2018, ICML.

[3]  Hyunsoo Kim,et al.  Learning to Discover Cross-Domain Relations with Generative Adversarial Networks , 2017, ICML.

[4]  Nikunj C. Oza,et al.  Online Ensemble Learning , 2000, AAAI/IAAI.

[5]  Bernt Schiele,et al.  Learning What and Where to Draw , 2016, NIPS.

[6]  Lawrence Carin,et al.  ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching , 2017, NIPS.

[7]  Eric P. Xing,et al.  Structured Generative Adversarial Networks , 2017, NIPS.

[8]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Andrea Vedaldi,et al.  It Takes (Only) Two: Adversarial Generator-Encoder Networks , 2017, AAAI.

[10]  Tom M. Mitchell,et al.  The Need for Biases in Learning Generalizations , 2007 .

[11]  Aaron C. Courville,et al.  Hierarchical Adversarially Learned Inference , 2018, ArXiv.

[12]  Allen and Rosenbloom Paul S. Newell,et al.  Mechanisms of Skill Acquisition and the Law of Practice , 1993 .

[13]  Guoyin Wang,et al.  JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets , 2018, ICML.

[14]  Bo Zhao,et al.  Modular Generative Adversarial Networks , 2018, ECCV.

[15]  John R. Anderson,et al.  MACHINE LEARNING An Artificial Intelligence Approach , 2009 .

[16]  Sebastian Ramos,et al.  The Cityscapes Dataset for Semantic Urban Scene Understanding , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Bernt Schiele,et al.  Generative Adversarial Text to Image Synthesis , 2016, ICML.

[18]  Sepp Hochreiter,et al.  GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium , 2017, NIPS.

[19]  Nick Craswell.  Mean Reciprocal Rank , 2009, Encyclopedia of Database Systems.

[20]  William J. McGill.  Multivariate information transmission , 1954, Trans. IRE Prof. Group Inf. Theory.

[21]  William Yang Wang,et al.  MojiTalk: Generating Emotional Responses at Scale , 2017, ACL.

[22]  Sanja Fidler,et al.  Skip-Thought Vectors , 2015, NIPS.

[23]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Alexei A. Efros,et al.  Context Encoders: Feature Learning by Inpainting , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Aaron C. Courville,et al.  Adversarially Learned Inference , 2016, ICLR.

[26]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[27]  Hanjiang Lai,et al.  Soft-Gated Warping-GAN for Pose-Guided Person Image Synthesis , 2018, NeurIPS.

[28]  Regina Barzilay,et al.  Style Transfer from Non-Parallel Text by Cross-Alignment , 2017, NIPS.

[29]  Taesung Park,et al.  CyCADA: Cycle-Consistent Adversarial Domain Adaptation , 2017, ICML.

[30]  Zhe Gan,et al.  Triangle Generative Adversarial Networks , 2017, NIPS.

[31]  Geoffrey E. Hinton,et al.  Dynamic Routing Between Capsules , 2017, NIPS.

[32]  Jan Kautz,et al.  Video-to-Video Synthesis , 2018, NeurIPS.

[33]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[34]  Arthur L. Samuel,et al.  Some studies in machine learning using the game of checkers , 2000, IBM J. Res. Dev..

[35]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[36]  Kou Tanaka,et al.  StarGAN-VC: non-parallel many-to-many Voice Conversion Using Star Generative Adversarial Networks , 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

[37]  Pat Langley,et al.  Crafting Papers on Machine Learning , 2000, ICML.

[38]  Michael Kearns,et al.  Computational complexity of machine learning , 1990, ACM distinguished dissertations.

[39]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[40]  Jung-Woo Ha,et al.  StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[41]  A. J. Bell.  THE CO-INFORMATION LATTICE , 2003 .