Imbalance-Robust and Sampling-Efficient Continuous Conditional GANs via Adaptive Vicinity and Auxiliary Regularization

• URL: http://arxiv.org/abs/2508.01725v3
• Date: Sat, 11 Oct 2025 16:24:51 GMT
• Title: Imbalance-Robust and Sampling-Efficient Continuous Conditional GANs via Adaptive Vicinity and Auxiliary Regularization
• Authors: Xin Ding, Yun Chen, Yongwei Wang, Kao Zhang, Sen Zhang, Peibei Cao, Xiangxue Wang,
• Abstract summary: We propose an enhanced CcGAN framework featuring two novel components for handling data imbalance.<n>The CcGAN framework's native one-step generator enables 30x-2000x faster inference than CCDM.
• Score: 15.273709585153009
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Recent advances in conditional generative modeling have introduced Continuous conditional Generative Adversarial Network (CcGAN) and Continuous Conditional Diffusion Model (CCDM) for estimating high-dimensional data distributions conditioned on scalar, continuous regression labels (e.g., angles, ages, or temperatures). However, these approaches face fundamental limitations: CcGAN suffers from data imbalance due to fixed-size vicinity constraints, while CCDM requires computationally expensive iterative sampling. To address these issues, we propose CcGAN-AVAR, an enhanced CcGAN framework featuring (1) two novel components for handling data imbalance - an adaptive vicinity mechanism that dynamically adjusts vicinity size and a multi-task discriminator that enhances generator training through auxiliary regression and density ratio estimation - and (2) the GAN framework's native one-step generator, enable 30x-2000x faster inference than CCDM. Extensive experiments on four benchmark datasets (64x64 to 256x256 resolution) across eleven challenging settings demonstrate that CcGAN-AVAR achieves state-of-the-art generation quality while maintaining sampling efficiency.

Related papers

• Function-Space Decoupled Diffusion for Forward and Inverse Modeling in Carbon Capture and Storage [65.51149575007149]
  We present Fun-DDPS, a generative framework that combines function-space diffusion models with differentiable neural operator surrogates for both forward and inverse modeling.<n>Fun-DDPS produces physically consistent realizations free from the high-frequency artifacts observed in joint-state baselines.
  arXiv  Detail & Related papers  (2026-02-12T18:58:12Z)
• Enhancing Diffusion-Based Quantitatively Controllable Image Generation via Matrix-Form EDM and Adaptive Vicinal Training [22.721395122355187]
  Continuous Conditional Diffusion Model (CCDM) is a diffusion-based framework designed to generate high-quality images conditioned on continuous regression labels.<n>We propose iCCDM, which incorporates the more advanced textitElucidated Diffusion Model (EDM) framework with substantial modifications to improve both generation quality and sampling efficiency.<n>Experiments on four benchmark datasets, spanning image resolutions from $64times64$ to $256times256$, demonstrate that iCCDM consistently outperforms existing methods.
  arXiv  Detail & Related papers  (2026-02-02T13:55:49Z)
• Controllable Probabilistic Forecasting with Stochastic Decomposition Layers [1.3995263206621]
  We introduce Decomposition Layers (SDL) for converting deterministic machine learning weather models into ensemble systems.<n>SDL applies learned perturbations at three decoder scales through latent-driven modulation, per-pixel noise, and channel scaling.<n>When applied to WXFormer via transfer learning, SDL requires less than 2% of the computational cost needed to train the baseline model.
  arXiv  Detail & Related papers  (2025-12-21T17:10:00Z)
• Adapformer: Adaptive Channel Management for Multivariate Time Series Forecasting [49.40321003932633]
  Adapformer is an advanced Transformer-based framework that merges the benefits of CI and CD methodologies through effective channel management.<n>Adapformer achieves superior performance over existing models, enhancing both predictive accuracy and computational efficiency.
  arXiv  Detail & Related papers  (2025-11-18T16:24:05Z)
• Composable Score-based Graph Diffusion Model for Multi-Conditional Molecular Generation [85.58520120011269]
  We propose Composable Score-based Graph Diffusion model (CSGD), which extends score matching to discrete graphs via concrete scores.<n>We show that CSGD achieves state-of-the-art performance with a 15.3% average improvement in controllability over prior methods.<n>Our findings highlight the practical advantages of score-based modeling for discrete graph generation and its capacity for flexible, multi-property molecular design.
  arXiv  Detail & Related papers  (2025-09-11T13:37:56Z)
• Advancing Reliable Test-Time Adaptation of Vision-Language Models under Visual Variations [67.35596444651037]
  Vision-language models (VLMs) exhibit remarkable zero-shot capabilities but struggle with distribution shifts in downstream tasks when labeled data is unavailable.<n>We propose a Reliable Test-time Adaptation (ReTA) method that enhances reliability from two perspectives.
  arXiv  Detail & Related papers  (2025-07-13T05:37:33Z)
• Adaptive Cubic Regularized Second-Order Latent Factor Analysis Model [14.755426957558868]
  High-dimensional and incompleteHDI datasets have become ubiquitous across various real-world applications.<n>We propose a two-fold approach to mitigate information instabilities.<n>The ACRS HDI demonstrate that the ALF represents higher representation than the faster advancing (SACR) models.
  arXiv  Detail & Related papers  (2025-07-03T03:15:54Z)
• MS$^3$D: A RG Flow-Based Regularization for GAN Training with Limited Data [16.574346252357653]
  We propose a novel regularization method based on the idea of renormalization group (RG) in physics. We show that our method can effectively enhance the performance and stability of GANs under limited data scenarios.
  arXiv  Detail & Related papers  (2024-08-20T18:37:37Z)
• CCDM: Continuous Conditional Diffusion Models for Image Generation [22.70942688582302]
  Conditional Diffusion Models (CDMs) offer a promising alternative to Continuous Conditional Generative Modeling (CCGM)<n>CDMs address existing limitations with specially designed conditional diffusion processes, a novel hard vicinal image denoising loss, and efficient conditional sampling procedures.<n>We demonstrate that CCDMs outperform state-of-the-art CCGM models, establishing a new benchmark.
  arXiv  Detail & Related papers  (2024-05-06T15:10:19Z)
• Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding [55.107555305760954]
  We propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. Our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.
  arXiv  Detail & Related papers  (2024-01-17T09:01:29Z)
• Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion [56.38386580040991]
  Consistency Trajectory Model (CTM) is a generalization of Consistency Models (CM) CTM enables the efficient combination of adversarial training and denoising score matching loss to enhance performance. Unlike CM, CTM's access to the score function can streamline the adoption of established controllable/conditional generation methods.
  arXiv  Detail & Related papers  (2023-10-01T05:07:17Z)
• DuDGAN: Improving Class-Conditional GANs via Dual-Diffusion [2.458437232470188]
  Class-conditional image generation using generative adversarial networks (GANs) has been investigated through various techniques. We propose a novel approach for class-conditional image generation using GANs called DuDGAN, which incorporates a dual diffusion-based noise injection process. Our method outperforms state-of-the-art conditional GAN models for image generation in terms of performance.
  arXiv  Detail & Related papers  (2023-05-24T07:59:44Z)
• Conditional Denoising Diffusion for Sequential Recommendation [62.127862728308045]
  Two prominent generative models, Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs) GANs suffer from unstable optimization, while VAEs are prone to posterior collapse and over-smoothed generations. We present a conditional denoising diffusion model, which includes a sequence encoder, a cross-attentive denoising decoder, and a step-wise diffuser.
  arXiv  Detail & Related papers  (2023-04-22T15:32:59Z)
• Breaking the Spurious Causality of Conditional Generation via Fairness Intervention with Corrective Sampling [77.15766509677348]
  Conditional generative models often inherit spurious correlations from the training dataset. This can result in label-conditional distributions that are imbalanced with respect to another latent attribute. We propose a general two-step strategy to mitigate this issue.
  arXiv  Detail & Related papers  (2022-12-05T08:09:33Z)
• Autoregressive Score Matching [113.4502004812927]
  We propose autoregressive conditional score models (AR-CSM) where we parameterize the joint distribution in terms of the derivatives of univariable log-conditionals (scores) For AR-CSM models, this divergence between data and model distributions can be computed and optimized efficiently, requiring no expensive sampling or adversarial training. We show with extensive experimental results that it can be applied to density estimation on synthetic data, image generation, image denoising, and training latent variable models with implicit encoders.
  arXiv  Detail & Related papers  (2020-10-24T07:01:24Z)
• Improving Generative Adversarial Networks with Local Coordinate Coding [150.24880482480455]
  Generative adversarial networks (GANs) have shown remarkable success in generating realistic data from some predefined prior distribution. In practice, semantic information might be represented by some latent distribution learned from data. We propose an LCCGAN model with local coordinate coding (LCC) to improve the performance of generating data.
  arXiv  Detail & Related papers  (2020-07-28T09:17:50Z)

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.