MonoFlow: Rethinking Divergence GANs via the Perspective of Wasserstein Gradient Flows

• URL: http://arxiv.org/abs/2302.01075v5
• Date: Tue, 8 Aug 2023 15:12:42 GMT
• Title: MonoFlow: Rethinking Divergence GANs via the Perspective of Wasserstein Gradient Flows
• Authors: Mingxuan Yi, Zhanxing Zhu, Song Liu
• Abstract summary: We introduce a unified generative modeling framework - MonoFlow. Under our framework, adversarial training can be viewed as a procedure first obtaining MonoFlow's vector field. We also reveal the fundamental difference between variational divergence minimization and adversarial training.
• Score: 34.795115757545915
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The conventional understanding of adversarial training in generative adversarial networks (GANs) is that the discriminator is trained to estimate a divergence, and the generator learns to minimize this divergence. We argue that despite the fact that many variants of GANs were developed following this paradigm, the current theoretical understanding of GANs and their practical algorithms are inconsistent. In this paper, we leverage Wasserstein gradient flows which characterize the evolution of particles in the sample space, to gain theoretical insights and algorithmic inspiration of GANs. We introduce a unified generative modeling framework - MonoFlow: the particle evolution is rescaled via a monotonically increasing mapping of the log density ratio. Under our framework, adversarial training can be viewed as a procedure first obtaining MonoFlow's vector field via training the discriminator and the generator learns to draw the particle flow defined by the corresponding vector field. We also reveal the fundamental difference between variational divergence minimization and adversarial training. This analysis helps us to identify what types of generator loss functions can lead to the successful training of GANs and suggest that GANs may have more loss designs beyond the literature (e.g., non-saturated loss), as long as they realize MonoFlow. Consistent empirical studies are included to validate the effectiveness of our framework.

Related papers

• Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching [60.37045080890305]
  We provide the first analysis of the sample complexity for flow-matching based generative models.<n>We decompose the velocity field estimation error into neural-network approximation error, statistical error due to the finite sample size, and optimization error due to the finite number of optimization steps for estimating the velocity field.
  arXiv  Detail & Related papers  (2025-12-01T05:14:25Z)
• Hierarchical Bayesian Flow Networks for Molecular Graph Generation [15.495256638671284]
  GraphBFN is a novel hierarchical coarse-to-fine framework based on Bayesian Flow Networks that operates on the parameters of distributions.<n>We demonstrate that our method achieves superior performance and faster generation, setting new state-of-the-art results on the QM9 and ZINC250k molecular graph generation benchmarks.
  arXiv  Detail & Related papers  (2025-10-11T13:27:55Z)
• Are We Really Learning the Score Function? Reinterpreting Diffusion Models Through Wasserstein Gradient Flow Matching [6.821102133726069]
  We present evidence that trained diffusion networks violate both integral and differential constraints required of true score functions.<n>We argue that diffusion training is better understood as flow matching to the velocity field of a Wasserstein Gradient Flow (WGF)<n>Our results advocate for adopting the WGF perspective as a principled, elegant, and theoretically grounded framework for understanding diffusion generative models.
  arXiv  Detail & Related papers  (2025-08-30T03:30:22Z)
• On Divergence Measures for Training GFlowNets [3.7277730514654555]
  Generative Flow Networks (GFlowNets) are amortized inference models designed to sample from unnormalized distributions over composable objects. Traditionally, the training procedure for GFlowNets seeks to minimize the expected log-squared difference between a proposal (forward policy) and a target (backward policy) distribution. We review four divergence measures, namely, Renyi-$alpha$'s, Tsallis-$alpha$'s, reverse and forward KL's, and design statistically efficient estimators for their gradients in the context of training GFlowNets
  arXiv  Detail & Related papers  (2024-10-12T03:46:52Z)
• Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding [84.3224556294803]
  Diffusion models excel at capturing the natural design spaces of images, molecules, DNA, RNA, and protein sequences. We aim to optimize downstream reward functions while preserving the naturalness of these design spaces. Our algorithm integrates soft value functions, which looks ahead to how intermediate noisy states lead to high rewards in the future.
  arXiv  Detail & Related papers  (2024-08-15T16:47:59Z)
• Improving Consistency Models with Generator-Induced Flows [16.049476783301724]
  Consistency models imitate the multi-step sampling of score-based diffusion in a single forward pass of a neural network. They can be learned in two ways: consistency distillation and consistency training. We propose a novel flow that transports noisy data towards their corresponding outputs derived from the currently trained model.
  arXiv  Detail & Related papers  (2024-06-13T20:22:38Z)
• A Differential Equation Approach for Wasserstein GANs and Beyond [1.2277343096128712]
  This paper proposes a new theoretical lens to view Wasserstein generative adversarial networks (WGANs) To minimize the Wasserstein-1 distance between the true data distribution and our estimate of it, we derive a distribution-dependent ordinary differential equation (ODE) This inspires a new class of generative models that naturally integrates persistent training (which we call W1-FE)
  arXiv  Detail & Related papers  (2024-05-25T21:03:39Z)
• Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models [59.331993845831946]
  Diffusion models benefit from instillation of task-specific information into the score function to steer the sample generation towards desired properties. This paper provides the first theoretical study towards understanding the influence of guidance on diffusion models in the context of Gaussian mixture models.
  arXiv  Detail & Related papers  (2024-03-03T23:15:48Z)
• Unsupervised Discovery of Interpretable Directions in h-space of Pre-trained Diffusion Models [63.1637853118899]
  We propose the first unsupervised and learning-based method to identify interpretable directions in h-space of pre-trained diffusion models. We employ a shift control module that works on h-space of pre-trained diffusion models to manipulate a sample into a shifted version of itself. By jointly optimizing them, the model will spontaneously discover disentangled and interpretable directions.
  arXiv  Detail & Related papers  (2023-10-15T18:44:30Z)
• Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization [87.21285093582446]
  Diffusion Generative Flow Samplers (DGFS) is a sampling-based framework where the learning process can be tractably broken down into short partial trajectory segments. Our method takes inspiration from the theory developed for generative flow networks (GFlowNets)
  arXiv  Detail & Related papers  (2023-10-04T09:39:05Z)
• Effective Dynamics of Generative Adversarial Networks [16.51305515824504]
  Generative adversarial networks (GANs) are a class of machine-learning models that use adversarial training to generate new samples. One major form of training failure, known as mode collapse, involves the generator failing to reproduce the full diversity of modes in the target probability distribution. We present an effective model of GAN training, which captures the learning dynamics by replacing the generator neural network with a collection of particles in the output space.
  arXiv  Detail & Related papers  (2022-12-08T22:04:01Z)
• Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation [110.09855163856326]
  This paper is about the problem of learning a policy for generating an object from a sequence of actions. We propose GFlowNet, based on a view of the generative process as a flow network. We prove that any global minimum of the proposed objectives yields a policy which samples from the desired distribution.
  arXiv  Detail & Related papers  (2021-06-08T14:21:10Z)
• Non-saturating GAN training as divergence minimization [22.459183156517728]
  We show that non-saturating generative adversarial network (GAN) training does in fact approximately minimize a particular f-divergence. These results help to explain the high sample quality but poor diversity often observed empirically when using this scheme.
  arXiv  Detail & Related papers  (2020-10-15T21:34:56Z)
• Unsupervised Controllable Generation with Self-Training [90.04287577605723]
  controllable generation with GANs remains a challenging research problem. We propose an unsupervised framework to learn a distribution of latent codes that control the generator through self-training. Our framework exhibits better disentanglement compared to other variants such as the variational autoencoder.
  arXiv  Detail & Related papers  (2020-07-17T21:50:35Z)
• Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator [85.68825725223873]
  Generative Adversarial Networks (GANs) have shown great promise in modeling high dimensional data. We introduce the Discriminator Contrastive Divergence, which is well motivated by the property of WGAN's discriminator. We demonstrate the benefits of significant improved generation on both synthetic data and several real-world image generation benchmarks.
  arXiv  Detail & Related papers  (2020-04-05T01:50:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.