Spectral Gradient Surgery for Domain-Generalizable Dataset Distillation

• URL: http://arxiv.org/abs/2605.18836v1
• Date: Wed, 13 May 2026 02:33:38 GMT
• Title: Spectral Gradient Surgery for Domain-Generalizable Dataset Distillation
• Abstract summary: We introduce Domain Generalizable dataset Distillation (DGDD)<n>We study the problem through a widely adopted Distribution Matching (DM) baseline.<n>We propose Spectral Gradient Surgery (SGS) to disentangle the two.
• Score: 6.809496808804485
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dataset Distillation (DD) synthesizes a compact synthetic dataset that preserves the training utility of a full dataset. However, its standard formulation assumes that test data follow the same distribution as training data, an assumption that rarely holds in practice. A straightforward extension-applying post-hoc Domain Generalization (DG) techniques to distilled data-is ill-suited because existing DG methods rely on the natural diversity of real datasets, which compact synthetic sets inherently lack, while also incurring substantial augmentation overhead that conflicts with the efficiency objective of dataset distillation. To address this limitation, we introduce Domain Generalizable Dataset Distillation (DGDD), a new problem setting that explicitly targets out-of-distribution (OOD) generalization of distilled datasets. We study this problem through a widely adopted DD baseline of Distribution Matching (DM). We attribute the OOD vulnerability of DM to the entanglement of class-discriminative and domain-specific information within the compressed synthetic set, and propose Spectral Gradient Surgery (SGS) to disentangle the two. The key insight of SGS is that cross-domain agreement among domain-wise gradients in the spectral domain reveals which gradient components are shared across source domains-and are therefore class-discriminative-and which are domain-specific. Based on this observation, SGS augments the standard DM update with two complementary gradients: one that reinforces cross-domain shared components and another that explicitly promotes diversity within the distilled dataset. Extensive experiments on diverse-scale benchmarks demonstrate that SGS substantially improves OOD generalization while remaining plug-and-play compatible with existing DM methods.

Related papers

• State Diversity Matters in Offline Behavior Distillation [58.116300485427764]
  We show that datasets with greater state diversity outperforms those with higher state quality when training loss is substantial.<n>We propose a novel yet simple algorithm, state density weighted (SDW) OBD, which emphasizes state diversity by weighting the distillation objective.
  arXiv  Detail & Related papers  (2025-12-07T06:55:08Z)
• Let Synthetic Data Shine: Domain Reassembly and Soft-Fusion for Single Domain Generalization [68.41367635546183]
  Single Domain Generalization aims to train models with consistent performance across diverse scenarios using data from a single source.<n>We propose Discriminative Domain Reassembly and Soft-Fusion (DRSF), a training framework leveraging synthetic data to improve model generalization.
  arXiv  Detail & Related papers  (2025-03-17T18:08:03Z)
• Progressive Multi-Level Alignments for Semi-Supervised Domain Adaptation SAR Target Recognition Using Simulated Data [3.1951121258423334]
  We develop an instance-prototype alignment (AIPA) strategy to push the source domain instances close to the corresponding target prototypes. We also develop an instance-prototype alignment (AIPA) strategy to push the source domain instances close to the corresponding target prototypes.
  arXiv  Detail & Related papers  (2024-11-07T13:53:13Z)
• Not All Samples Should Be Utilized Equally: Towards Understanding and Improving Dataset Distillation [57.6797306341115]
  We take an initial step towards understanding various matching-based DD methods from the perspective of sample difficulty.<n>We then extend the neural scaling laws of data pruning to DD to theoretically explain these matching-based methods.<n>We introduce the Sample Difficulty Correction (SDC) approach, designed to predominantly generate easier samples to achieve higher dataset quality.
  arXiv  Detail & Related papers  (2024-08-22T15:20:32Z)
• Disentangling Masked Autoencoders for Unsupervised Domain Generalization [57.56744870106124]
  Unsupervised domain generalization is fast gaining attention but is still far from well-studied. Disentangled Masked Auto (DisMAE) aims to discover the disentangled representations that faithfully reveal intrinsic features. DisMAE co-trains the asymmetric dual-branch architecture with semantic and lightweight variation encoders.
  arXiv  Detail & Related papers  (2024-07-10T11:11:36Z)
• Semi Supervised Heterogeneous Domain Adaptation via Disentanglement and Pseudo-Labelling [4.33404822906643]
  Semi-supervised domain adaptation methods leverage information from a source labelled domain to generalize over a scarcely labelled target domain. Such a setting is denoted as Semi-Supervised Heterogeneous Domain Adaptation (SSHDA) We introduce SHeDD (Semi-supervised Heterogeneous Domain Adaptation via Disentanglement) an end-to-end neural framework tailored to learning a target domain.
  arXiv  Detail & Related papers  (2024-06-20T08:02:49Z)
• Cross Domain Generative Augmentation: Domain Generalization with Latent Diffusion Models [11.309433257851122]
  Cross Domain Generative Augmentation (CDGA) generates synthetic images to fill the gap between all domains. We show that CDGA outperforms SOTA DG methods under the Domainbed benchmark.
  arXiv  Detail & Related papers  (2023-12-08T21:52:00Z)
• FSDA-DG: Improving Cross-Domain Generalizability of Medical Image Segmentation with Few Source Domain Annotations [10.362970759633543]
  We propose FSDA-DG, a novel solution to improve cross-domain generalizability of medical image segmentation with few single-source domain annotations.<n>FSDA-DG divides images into global broad regions and semantics-guided local regions, and applies distinct augmentation strategies to enrich data distribution.
  arXiv  Detail & Related papers  (2023-11-05T07:44:40Z)
• Domain Generalization with Adversarial Intensity Attack for Medical Image Segmentation [27.49427483473792]
  In real-world scenarios, it is common for models to encounter data from new and different domains to which they were not exposed to during training. domain generalization (DG) is a promising direction as it enables models to handle data from previously unseen domains. We introduce a novel DG method called Adversarial Intensity Attack (AdverIN), which leverages adversarial training to generate training data with an infinite number of styles.
  arXiv  Detail & Related papers  (2023-04-05T19:40:51Z)
• Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning [122.62311703151215]
  Divide and Contrast (DaC) aims to connect the good ends of both worlds while bypassing their limitations. DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals. We further align the source-like domain with the target-specific samples using a memory bank-based Maximum Mean Discrepancy (MMD) loss to reduce the distribution mismatch.
  arXiv  Detail & Related papers  (2022-11-12T09:21:49Z)
• Generalizable Representation Learning for Mixture Domain Face Anti-Spoofing [53.82826073959756]
  Face anti-spoofing approach based on domain generalization(DG) has drawn growing attention due to its robustness forunseen scenarios. We propose domain dy-namic adjustment meta-learning (D2AM) without using do-main labels. To overcome the limitation, we propose domain dy-namic adjustment meta-learning (D2AM) without using do-main labels.
  arXiv  Detail & Related papers  (2021-05-06T06:04:59Z)

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.