# Group Distributionally Robust Knowledge Distillation

arXiv: https://arxiv.org/abs/2311.00476 · HTML: https://mlsanity.com/paper/2311.00476/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 11 of its 13 references that are in the map.
- First posted on arXiv 1 Nov 2023.

## Placed in

- Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/)

## Builds on (most cited first, 11 of 11)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [Environment Inference for Invariant Learning](https://mlsanity.com/paper/2010.07249/) (2020)
- [Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations](https://mlsanity.com/paper/2203.01517/) (2022)
- [Whole-Slide Mitosis Detection in H&E Breast Histology Using PHH3 as a Reference to Train Distilled Stain-Invariant Convolutional Networks](https://mlsanity.com/paper/1808.05896/) (2018)
- [Relational Subsets Knowledge Distillation for Long-tailed Retinal Diseases Recognition](https://mlsanity.com/paper/2104.11057/) (2021)
- [What Knowledge Gets Distilled in Knowledge Distillation?](https://mlsanity.com/paper/2205.16004/) (2022)
- [Robust Distillation for Worst-class Performance](https://mlsanity.com/paper/2206.06479/) (2022)

## Built on by (most cited first, 3 of 3)

- [Group Distributionally Robust Dataset Distillation with Risk Minimization](https://mlsanity.com/paper/2402.04676/) (2024)
- [Does Weak-to-strong Generalization Happen under Spurious Correlations?](https://mlsanity.com/paper/2509.24005/) (2025)
- [Camera clustering for scalable stream-based active distillation](https://mlsanity.com/paper/2404.10411/) (2024)

## Abstract (arXiv)

Knowledge distillation enables fast and effective transfer of features learned from a bigger model to a smaller one. However, distillation objectives are susceptible to sub-population shifts, a common scenario in medical imaging analysis which refers to groups/domains of data that are underrepresented in the training set. For instance, training models on health data acquired from multiple scanners or hospitals can yield subpar performance for minority groups. In this paper, inspired by distributionally robust optimization (DRO) techniques, we address this shortcoming by proposing a group-aware distillation loss. During optimization, a set of weights is updated based on the per-group losses at a given iteration. This way, our method can dynamically focus on groups that have low performance during training. We empirically validate our method, GroupDistil on two benchmark datasets (natural images and cardiac MRIs) and show consistent improvement in terms of worst-group accuracy.