Four eyes see more than two: Dataset Distillation with Mixture-of-Experts


Jia-Jiun Yao (National Yang Ming Chiao Tung University), Sheng-Feng Yu (National Yang Ming Chiao Tung University, Macronix International Co., Ltd.), Wei-Chen Chiu (National Yang Ming Chiao Tung University)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

The ever-growing size of datasets in deep learning presents a significant challenge in terms of training efficiency and computational cost. Dataset distillation (DD) has emerged as a promising approach to address this challenge by generating compact synthetic datasets that retain the essential information of the original data. However, existing DD methods often suffer from performance degradation when transferring distilled datasets across different network architectures (i.e. the model utilizing distilled dataset for further training is different from the one used in dataset distillation). To overcome this limitation, we propose a novel mixture-of-experts framework for dataset distillation. Our goal focuses on promoting diversity within the distilled dataset by distributing the distillation tasks to multiple expert models. Each expert specializes in distilling a distinct subset of the dataset, encouraging them to capture different aspects of the original data distribution. To further enhance diversity, we introduce a distance correlation minimization strategy to encourage the experts to learn distinct representations. Moreover, during the testing stage (where the distilled dataset is used for training a new model), the mixup-based fusion strategy is applied to better leverage the complementary information captured by each expert. Through extensive experiments, we demonstrate that our framework effectively mitigates the issue of cross-architecture performance degradation in dataset distillation, particularly in low-data regimes, leading to more efficient and versatile deep learning models while being trained upon the distilled dataset.

Citation

@inproceedings{Yao_2025_BMVC,
author    = {Jia-Jiun Yao and Sheng-Feng Yu and Wei-Chen Chiu},
title     = {Four eyes see more than two: Dataset Distillation with Mixture-of-Experts},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_165/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection