Wasserstein Auto-Encoders

We propose the Wasserstein Auto-Encoder (WAE)---a new algorithm for building a generative model of the data distribution. WAE minimizes a penalized form of the Wasserstein distance between the model distribution and the target distribution, which leads to a different regularizer than the one used by the Variational Auto-Encoder (VAE). This regularizer encourages the encoded training distribution to match the prior. We compare our algorithm with several other techniques and show that it is a generalization of adversarial auto-encoders (AAE). Our experiments show that WAE shares many of the properties of VAEs (stable training, encoder-decoder architecture, nice latent manifold structure) while generating samples of better quality, as measured by the FID score.

• Publication year

  2017

• Venue

  International Conference on Learning Representations

• Publication date

  2017-11-05

• Fields of study

  Mathematics, Computer Science

• Identifiers
  arXiv 1711.01558
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Bio-inspired synthesis of xishacorenes A, B, and C, and a new congener from fuscol

  2019cited by this paper
• and s

  2019cited by this paper
• GENERATIVE ADVERSARIAL NETS

  2018influential reference
• It Takes (Only) Two: Adversarial Generator-Encoder Networks

  2017cited by this paper
• From optimal transport to generative modeling: the VEGAN cookbook

  2017influential reference
• Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks

  2017cited by this paper
• MMD GAN: Towards Deeper Understanding of Moment Matching Network

  2017cited by this paper
• InfoVAE: Information Maximizing Variational Autoencoders

  2017cited by this paper
• Improved Training of Wasserstein GANs

  2017cited by this paper
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

  2017cited by this paper
• BEGAN: Boundary Equilibrium Generative Adversarial Networks

  2017cited by this paper
• f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization

  2016cited by this paper
• Adversarially Learned Inference

  2016cited by this paper
• Identity Mappings in Deep Residual Networks

  2016cited by this paper
• Stochastic Optimization for Large-scale Optimal Transport

  2016cited by this paper
• Improved generator objectives for GANs

  2016cited by this paper
• Energy-based Generative Adversarial Network

  2016cited by this paper
• Supplementary Materials for : “ f-GAN : Training Generative Neural Samplers using Variational Divergence Minimization ”

  2016cited by this paper
• Adversarial Autoencoders

  2015influential reference
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

  2015cited by this paper
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

  2015cited by this paper
• On the High Dimensional Power of a Linear-Time Two Sample Test under Mean-shift Alternatives

  2015cited by this paper
• Training generative neural networks via Maximum Mean Discrepancy optimization

  2015cited by this paper
• Optimal Entropy-Transport problems and a new Hellinger–Kantorovich distance between positive measures

  2015cited by this paper
• Generative Moment Matching Networks

  2015cited by this paper
• Unbalanced Optimal Transport: Geometry and Kantorovich Formulation

  2015cited by this paper
• Adam: A Method for Stochastic Optimization

  2014influential reference
• Deep Learning Face Attributes in the Wild

  2014influential reference
• Auto-Encoding Variational Bayes

  2013influential reference
• Sinkhorn Distances: Lightspeed Computation of Optimal Transport

  2013cited by this paper
• Representation Learning: A Review and New Perspectives

  2012cited by this paper
• A Kernel Two-Sample Test

  2012cited by this paper
• Topics in Optimal Transportation

  2003cited by this paper
• Statistical Decision Theory

  2000cited by this paper
• Gradient-based learning applied to document recognition

  1998influential reference
• A and V

  1962cited by this paper
• Book Reviews

  1893influential reference

• CTTVAE: Latent Space Structuring for Conditional Tabular Data Generation on Imbalanced Datasets

  2026influential citation
• Data Augmentation for High-Fidelity Generation of CAR-T/NK Immunological Synapse Images

  2026cites this paper
• Bayesian Experimental Design for Model Discrepancy Calibration: A Rivalry between Kullback-Leibler Divergence and Wasserstein Distance

  2026cites this paper
• Image Generation with a Sphere Encoder

  2026cites this paper
• Prior Distribution Guided Gaussian Mixture Variational Autoencoder (PDGM-VAE) for Image Generation

  2026cites this paper
• Predicting human decision-making across task conditions via individuality transfer

  2026cites this paper
• Learning a Latent Pulse Shape Interface for Photoinjector Laser Systems

  2026cites this paper
• Optimal Transport-Induced Samples against Out-of-Distribution Overconfidence

  2026cites this paper
• Variational Sparse Paired Autoencoders (vsPAIR) for Inverse Problems and Uncertainty Quantification

  2026cites this paper
• MePAT: Meta-Prior Aided Transformer for Adverse Weather Condition Restoration

  2026cites this paper
• Physics-Constrained Denoising Autoencoders for Data-Scarce Wildfire UAV Sensing

  2026cites this paper
• Distributional Active Inference

  2026cites this paper
• Toward Generalist Neural Motion Planners for Robotic Manipulators: Challenges and Opportunities

  2026cites this paper
• Variational and Generative Models With Quantization for Disentanglement and Compressed Sensing of GNSS Spectrograms

  2026cites this paper
• Well-Posed KL-Regularized Control via Wasserstein and Kalman-Wasserstein KL Divergences

  2026cites this paper
• Molecular Design beyond Training Data with Novel Extended Objective Functionals of Generative AI Models Driven by Quantum Annealing Computer

  2026cites this paper
• Functional Diversity in Deep Ensembles via Wasserstein Representation Alignment

  2026cites this paper
• RPWAEAuth: Sensor-Based Continuous Authentication Using Reconstruction Probability in Wasserstein Autoencoder

  2025cites this paper
• A Novel Wasserstein Quaternion Generative Adversarial Network for Color Image Generation

  2025cites this paper
• Towards Unsupervised Causal Representation Learning via Latent Additive Noise Model Causal Autoencoders

  2025influential citation
• Partial Inverse Design of High-Performance Concrete Using Cooperative Neural Networks for Constraint-Aware Mix Generation

  2025cites this paper
• Generative models for antimicrobial peptide design: auto-encoders and beyond

  2025influential citation
• Deep Latent Space Based Data Assimilation Method for Integrating Multiple Body Tracking Techniques for Immersive XR Applications

  2025cites this paper
• Deep Learning From Diffuse Optical Oximetry Time-Series: An fNIRS-Focused Review of Recent Advancements and Future Directions

  2025cites this paper
• Cross-Network Relationship Learning via Optimal Transport for Link Prediction

  2025cites this paper
• VDOT: Efficient Unified Video Creation via Optimal Transport Distillation

  2025cites this paper
• Reinforcement-Learning Portfolio Allocation with Dynamic Embedding of Market Information

  2025influential citation
• Disentanglement Analysis in Deep Latent Variable Models Matching Aggregate Posterior Distributions

  2025cites this paper
• A sliced Wasserstein and diffusion approach to random coefficient models

  2025cites this paper
• A Comprehensive Survey on Imbalanced Data Learning

  2025cites this paper
• Lightweight Wasserstein Audio-Visual Model for Unified Speech Enhancement and Separation

  2025cites this paper
• Use of autoencoders to improve the accuracy of thin-layer chromatography

  2025cites this paper
• Geometric Autoencoder Priors for Bayesian Inversion: Learn First Observe Later

  2025cites this paper
• Cloud Model Characteristic Function Auto-Encoder: Integrating Cloud Model Theory with MMD Regularization for Enhanced Generative Modeling

  2025influential citation
• Approximation Analysis of the Entropic Penalty in Quadratic Programming

  2025cites this paper
• RankGuess: Password Guessing Using Adversarial Ranking

  2025cites this paper
• Distributed Keyword-guided Topic Model with Lexical Knowledge Supervision

  2025cites this paper
• A comparison of latent space modeling techniques in a plain-vanilla autoencoder setting

  2025cites this paper
• Equivariant diffusion for structure-based de novo ligand generation with latent-conditioning

  2025cites this paper
• S2WTM: Spherical Sliced-Wasserstein Autoencoder for Topic Modeling

  2025cites this paper
• Imaging 3D polarization dynamics via deep learning 4D-STEM

  2025influential citation
• Variational Inference Optimized Using the Curved Geometry of Coupled Free Energy

  2025cites this paper
• Robust Intrusion Detection for Industrial Control System

  2025influential citation
• Information-Preserving CSI Feedback: Invertible Networks with Endogenous Quantization and Channel Error Mitigation

  2025cites this paper
• ViTCAE: ViT-based Class-conditioned Autoencoder

  2025cites this paper
• Learn from Global Rather Than Local: Consistent Context-Aware Representation Learning for Multi-View Graph Clustering

  2025cites this paper
• Ordinal Label-Distribution Learning with Constrained Asymmetric Priors for Imbalanced Retinal Grading

  2025cites this paper
• LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching

  2025cites this paper
• Matricial Free Energy as a Gaussianizing Regularizer: Enhancing Autoencoders for Gaussian Code Generation

  2025cites this paper
• Enhancing Few-Shot Classification of Benchmark and Disaster Imagery with ATTBHFA-Net

  2025influential citation
• Deep generative approaches for oversampling in imbalanced data classification problems: A comprehensive review and comparative analysis

  2025cites this paper
• Towards a More Efficient Sinkhorn Distance Computation in Neural Topic Models

  2025cites this paper
• Your contrastive learning problem is secretly a distribution alignment problem

  2025cites this paper
• Convex relaxation approaches for high-dimensional optimal transport

  2025cites this paper
• ARD-VAE: A Statistical Formulation to Find the Relevant Latent Dimensions of Variational Autoencoders

  2025influential citation
• UniTrans: A Unified Vertical Federated Knowledge Transfer Framework for Enhancing Cross-Hospital Collaboration

  2025cites this paper
• Deep Generative Models for Therapeutic Peptide Discovery: A Comprehensive Review

  2025cites this paper
• Multi-view deep generative dual fusion network for zero-shot learning

  2025cites this paper
• Learning with Differentially Private (Sliced) Wasserstein Gradients

  2025cites this paper
• Minimax Lower Bounds for Estimating Distributions on Low-dimensional Spaces

  2025cites this paper
• Advances of deep Neural Networks (DNNs) in the development of peptide drugs.

  2025cites this paper
• EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling

  2025cites this paper
• Latent Representation Learning in Physics‐Informed Neural Networks for Full Waveform Inversion

  2025cites this paper
• Variational Rank Reduction Autoencoder

  2025cites this paper
• Streaming Sliced Optimal Transport

  2025cites this paper
• From KL Divergence to Wasserstein Distance: Enhancing Autoencoders with FID Analysis

  2025influential citation
• A Dictionary of Closed-Form Kernel Mean Embeddings

  2025cites this paper
• Enhancing the Classification of Imbalanced Arabic Medical Questions Using DeepSMOTE

  2025cites this paper
• Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis

  2025cites this paper
• Extraction of implicit field cost via inverse optimal Schrödinger bridge

  2025cites this paper
• Efficient Variants of Wasserstein Distance in Hyperbolic Space via Space-Filling Curve Projection

  2025influential citation
• A Framework for Neural Topic Modeling with Mutual Information and Group Regularization

  2025cites this paper
• Likelihood-Free Variational Autoencoders

  2025cites this paper
• Augmenting Perceptual Super-Resolution via Image Quality Predictors

  2025cites this paper
• SV-SAE: Layer-Wise Pruning for Autoencoder Based on Link Contributions

  2025cites this paper
• Effective latent hierarchical feature fusion in multiple instance learning for Whole Slide Image classification

  2025cites this paper
• Good Things Come in Pairs: Paired Autoencoders for Inverse Problems

  2025cites this paper
• Fully Dynamic Euclidean Bi-Chromatic Matching in Sublinear Update Time

  2025cites this paper
• Neural Conditional Transport Maps

  2025cites this paper
• WEISS: Wasserstein efficient sampling strategy for LLMs in drug design

  2025cites this paper
• Joint-stochastic-approximation Autoencoders with Application to Semi-supervised Learning

  2025cites this paper
• Symmetric Regularized Sequential Latent Variable Models With Adversarial Neural Networks

  2025cites this paper
• Neural Estimation for Scaling Entropic Multimarginal Optimal Transport

  2025cites this paper
• Information preservation with wasserstein autoencoders: generation consistency and adversarial robustness

  2025influential citation
• VIVAT: Virtuous Improving VAE Training through Artifact Mitigation

  2025cites this paper
• Ground Reaction Force Estimation via Time-Aware Knowledge Distillation

  2025cites this paper
• Visual Variational Autoencoder Prompt Tuning

  2025cites this paper
• An improved central limit theorem for the empirical sliced Wasserstein distance

  2025cites this paper
• History Matching under Uncertainty of Geological Scenarios with Implicit Geological Realism Control with Generative Deep Learning and Graph Convolutions

  2025cites this paper
• UniTrans: A Unified Vertical Federated Knowledge Transfer Framework for Enhancing Edge Healthcare Collaboration

  2025cites this paper
• Control, Optimal Transport and Neural Differential Equations in Supervised Learning

  2025cites this paper
• MorphGen: Morphology-Guided Representation Learning for Robust Single-Domain Generalization in Histopathological Cancer Classification

  2025cites this paper
• Hardware-Aware Bayesian Neural Architecture Search of Quantized CNNs

  2025cites this paper
• Machine learning‐based research of new refractory high‐entropy alloys using guided multiobjectives search strategy

  2025cites this paper
• On the design and evaluation of generative models in high energy density physics

  2025cites this paper
• GMCWAE: A Representation Learning Technique for Network Intrusion Detection in IoT

  2025cites this paper
• CINDES: Classification induced neural density estimator and simulator

  2025cites this paper
• Learning Energy-based Variational Latent Prior for VAEs

  2025cites this paper
• Benchmarking 3D generative autoencoders for pseudo-healthy reconstruction of brain 18F-fluorodeoxyglucose positron emission tomography

  2025influential citation
• Debiasing Kernel-Based Generative Models

  2025cites this paper