Method · Diffusion-based synthesis
Optimizing Distributional Geometry Alignment with Optimal Transport for Generative Dataset Distillation
Xiao Cui, Yulei Qin, Wengang Zhou, Hongsheng Li, Houqiang Li
NeurIPS 2025 · first public 2025-11-29 · arXiv 2512.00308
In one paragraph
Reformulates generative dataset distillation as Optimal Transport distance minimization to capture instance-level and intra-class geometry that global mean/variance matching misses, with three components: OT-guided diffusion sampling that aligns latent distributions, label-image-aligned soft relabeling that adapts label distributions to the complexity of the distilled images, and OT-based logit matching between student outputs and soft-label distributions; reports at least a 4% accuracy gain over the state of the art at IPC=10 on ImageNet-1K across architectures.
Where it sits
- Diffusion-based synthesis (Generative priors)
- Label distillation and soft labels (Orthogonal design choices)
- Setting: Image classification
Design choices
| Labels | soft-relabel |
Abstract (verbatim from arXiv)
Dataset distillation seeks to synthesize a compact distilled dataset, enabling models trained on it to achieve performance comparable to models trained on the full dataset. Recent methods for large-scale datasets focus on matching global distributional statistics (e.g., mean and variance), but overlook critical instance-level characteristics and intraclass variations, leading to suboptimal generalization. We address this limitation by reformulating dataset distillation as an Optimal Transport (OT) distance minimization problem, enabling fine-grained alignment at both global and instance levels throughout the pipeline. OT offers a geometrically faithful framework for distribution matching. It effectively preserves local modes, intra-class patterns, and fine-grained variations that characterize the geometry of complex, high-dimensional distributions. Our method comprises three components tailored for preserving distributional geometry: (1) OT-guided diffusion sampling, which aligns latent distributions of real and distilled images; (2) label-image-aligned soft relabeling, which adapts label distributions based on the complexity of distilled image distributions; and (3) OT-based logit matching, which aligns the output of student models with soft-label distributions. Extensive experiments across diverse architectures and large-scale datasets demonstrate that our method consistently outperforms state-of-the-art approaches in an efficient manner, achieving at least 4% accuracy improvement under IPC=10 settings for each architecture on ImageNet-1K.
BibTeX (generated; prefer the venue's official entry)
@article{cui2025optimizing,
title = {Optimizing Distributional Geometry Alignment with Optimal Transport for Generative Dataset Distillation},
author = {Xiao Cui and Yulei Qin and Wengang Zhou and Hongsheng Li and Houqiang Li},
journal = {NeurIPS 2025},
year = {2025}
}Nearby in Diffusion-based synthesis
Learnability-guided diffusion — Learnability-Guided Diffusion for Dataset Distillation
Jeffrey A. Chan-Santiago, Mubarak Shah · CVPR 2026notablepaper ↗
ManifoldGD — ManifoldGD: Training-Free Hierarchical Manifold Guidance for Diffusion-Based Dataset Distillation
Ayush Roy, Wei-Yang Alex Lee, Rudrasis Chakraborty et al. · CVPR 2026notablepaper ↗code ↗