# Role-Wise Data Augmentation for Knowledge Distillation

arXiv: https://arxiv.org/abs/2004.08861 · HTML: https://mlsanity.com/paper/2004.08861/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2020.

## Built on by (most cited first, 8 of 8)

- [RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation](https://mlsanity.com/paper/2109.10164/) (2021)
- [Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve Backbones](https://mlsanity.com/paper/2103.05959/) (2021)
- [Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax](https://mlsanity.com/paper/2105.13608/) (2021)
- [Dataset Distillation via Adversarial Prediction Matching](https://mlsanity.com/paper/2312.08912/) (2023)
- [How to Select One Among All? An Extensive Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding](https://mlsanity.com/paper/2109.05696/) (2021)
- [Comparative Knowledge Distillation](https://mlsanity.com/paper/2311.02253/) (2023)
- [Knowledge Distillation with Noisy Labels for Natural Language Understanding](https://mlsanity.com/paper/2109.10147/) (2021)
- [Revisiting Data Augmentation in Model Compression: An Empirical and Comprehensive Study](https://mlsanity.com/paper/2305.13232/) (2023)

## Abstract (arXiv)

Knowledge Distillation (KD) is a common method for transferring the ``knowledge'' learned by one machine learning model (the textitteacher) into another model (the textitstudent), where typically, the teacher has a greater capacity (e.g., more parameters or higher bit-widths). To our knowledge, existing methods overlook the fact that although the student absorbs extra knowledge from the teacher, both models share the same input data -- and this data is the only medium by which the teacher's knowledge can be demonstrated. Due to the difference in model capacities, the student may not benefit fully from the same data points on which the teacher is trained. On the other hand, a human teacher may demonstrate a piece of knowledge with individualized examples adapted to a particular student, for instance, in terms of her cultural background and interests. Inspired by this behavior, we design data augmentation agents with distinct roles to facilitate knowledge distillation. Our data augmentation agents generate distinct training data for the teacher and student, respectively. We find empirically that specially tailored data points enable the teacher's knowledge to be demonstrated more effectively to the student. We compare our approach with existing KD methods on training popular neural architectures and demonstrate that role-wise data augmentation improves the effectiveness of KD over strong prior approaches. The code for reproducing our results can be found at https://github.com/bigaidream-projects/role-kd