Distributed Parallel Gradient Stacking(DPGS): Solving Whole Slide Image Stacking Challenge in Multi-Instance Learning

Boyuan Wu; ZEFENG WANG; Xianwei Lin; Jiachun Xu; Jikai Yu; Zhou Shicheng; Hongda Chen; Lianxin Hu

ICML 2025poster0 citations

Distributed Parallel Gradient Stacking(DPGS): Solving Whole Slide Image Stacking Challenge in Multi-Instance Learning

Boyuan Wu, ZEFENG WANG, Xianwei Lin, Jiachun Xu, Jikai Yu, Zhou Shicheng, Hongda Chen, Lianxin Hu

Abstract

Whole Slide Image (WSI) analysis is framed as a Multiple Instance Learning (MIL) problem, but existing methods struggle with non-stackable data due to inconsistent instance lengths, which degrades performance and efficiency. We propose a Distributed Parallel Gradient Stacking (DPGS) framework with Deep Model-Gradient Compression (DMGC) to address this. DPGS enables lossless MIL data stacking for the first time, while DMGC accelerates distributed training via joint gradient-model compression. Experiments on Camelyon16 and TCGA-Lung datasets demonstrate up to 31× faster training, up to a 99.2% reduction in model communication size at convergence, and up to a 9.3% improvement in accuracy compared to the baseline. To our knowledge, this is the first work to solve non-stackable data in MIL while improving both speed and accuracy.

Multi-Instance Learning ，Distributed Training，Gradient Compression，Whole Slide Image Analysis，Medical Image Classification

BibTeX

@inproceedings{
wu2025distributed,
title={Distributed Parallel Gradient Stacking({DPGS}): Solving Whole Slide Image Stacking Challenge in Multi-Instance Learning},
author={Boyuan Wu and ZEFENG WANG and Xianwei Lin and Jiachun Xu and Jikai Yu and Zhou Shicheng and Hongda Chen and Lianxin Hu},
booktitle={Forty-second International Conference on Machine Learning},
year={2025},
url={https://openreview.net/forum?id=ss5JNmJDkW}
}