Data to 14 Oct 2026

MMD GAN: Towards Deeper Understanding of Moment Matching Network

arXiv 1705.08584 ↗First posted 24 May 2017cs.LG cs.AI stat.MLcited by 254

Not on the map. Why?

Cited by 20 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Generative moment matching network (GMMN) is a deep generative model that differs from Generative Adversarial Network (GAN) by replacing the discriminator in GAN with a two-sample test based on kernel maximum mean discrepancy (MMD). Although some theoretical guarantees of MMD have been studied, the empirical performance of GMMN is still not as competitive as that of GAN on challenging and large benchmark datasets. The computational efficiency of GMMN is also less desirable in comparison with GAN, partially due to its requirement for a rather large batch size during the training. In this paper, we propose to improve both the model expressiveness of GMMN and its computational efficiency by introducing adversarial kernel learning techniques, as the replacement of a fixed Gaussian kernel in the original GMMN. The new approach combines the key ideas in both GMMN and GAN, hence we name it MMD GAN. The new distance measure in MMD GAN is a meaningful loss that enjoys the advantage of weak topology and can be optimized via gradient descent with relatively small batch sizes. In our evaluation on multiple benchmark datasets, including MNIST, CIFAR- 10, CelebA and LSUN, the performance of MMD-GAN significantly outperforms GMMN, and is competitive with other representative GAN works.

Key facts. Cited by 254 papers in the map (data through 14 Oct 2026). First posted on arXiv 24 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 2; 2021: 62; 2022: 38; 2023: 46; 2024: 37; 2025: 35; 2026: 34.

254 papers.

Sort:

By area:

2023Multisample Flow Matching: Straightening Flows with Minibatch Couplingscited by 278
2022Diffusion-GAN: Training GANs with Diffusioncited by 205
2021TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Upcited by 162
2021Neural SDEs as Infinite-Dimensional GANscited by 161
2025Inductive Moment Matchingcited by 113
2021Recent advances and clinical applications of deep learning in medical image analysiscited by 104
2024Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspectivecited by 89
2023Optimizing DDPM Sampling with Shortcut Fine-Tuningcited by 81
2021Efficient and Accurate Gradients for Neural SDEscited by 71
2021Domain Adaptation for Time Series Forecasting via Attention Sharingcited by 68
2020f-IRL: Inverse Reinforcement Learning via State Marginal Matchingcited by 67
2022Synthetic Data -- what, why and how?cited by 67

38 more

2021Towards Discovery and Attribution of Open-world GAN Generated Imagescited by 66
2021Minibatch optimal transport distances; analysis and applicationscited by 65
2021Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Imagescited by 58
2022Generative Multiplane Images: Making a 2D GAN 3D-Awarecited by 57
2021Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorizationcited by 52
2024Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Stepcited by 47
2022Unbalanced Optimal Transport, from Theory to Numericscited by 46
2025Dataset Distillation with Neural Characteristic Function: A Minmax Perspectivecited by 45
2021Neural Mean Discrepancy for Efficient Out-of-Distribution Detectioncited by 42
2022StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesiscited by 38
2021Estimating and Evaluating Regression Predictive Uncertainty in Deep Object Detectorscited by 37
2021DISSECT: Disentangled Simultaneous Explanations via Concept Traversalscited by 37
2021KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Supportcited by 37
2021Probabilistic Forecasting with Generative Networks via Scoring Rule Minimizationcited by 37
2023Generative Sliced MMD Flows with Riesz Kernelscited by 37
2023Trainability barriers and opportunities in quantum generative modelingcited by 36
2023Free Lunch for Domain Adversarial Training: Environment Label Smoothingcited by 33
2024DySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic Systemscited by 30
2020On Computation and Generalization of Generative Adversarial Imitation Learningcited by 28
2021Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspectivecited by 25
2025Distributional Diffusion Models with Scoring Rulescited by 25
2026Sinkhorn-Drifting Generative Modelscited by 24
2021Pareto GAN: Extending the Representational Power of GANs to Heavy-Tailed Distributionscited by 23
2021PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learningcited by 23
2021Disentangled Recurrent Wasserstein Autoencodercited by 22
2022Nystr"om Kernel Mean Embeddingscited by 22
2021A Neural Tangent Kernel Perspective of GANscited by 21
2022PI-VAE: Physics-Informed Variational Auto-Encoder for stochastic differential equationscited by 21
2023DiME: Maximizing Mutual Information by a Difference of Matrix-Based Entropiescited by 21
2024Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Learningcited by 20
2023Complexity Matters: Rethinking the Latent Space for Generative Modelingcited by 19
2024Deep MMD Gradient Flow without adversarial trainingcited by 19
2023Deep Generative Models for Detector Signature Simulation: A Taxonomic Reviewcited by 18
2021Deep Co-Attention Network for Multi-View Subspace Learningcited by 17
2024A Distributional Analogue to the Successor Representationcited by 17
2021Composite Goodness-of-fit Tests with Kernelscited by 16
2023Constrained Policy Optimization with Explicit Behavior Density for Offline Reinforcement Learningcited by 16
2021Neural Tangent Kernel Maximum Mean Discrepancycited by 15

50 most cited of 254 All 254 (JSON)