# A Controlled Study of Feature-Based Knowledge Distillation Across Student Designs

arXiv: https://arxiv.org/abs/2608.08294 · HTML: https://mlsanity.com/paper/2608.08294/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 8 of its 12 references that are in the map.
- First posted on arXiv 8 Aug 2026.

## Placed in

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

## Builds on (most cited first, 8 of 8)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [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)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [On the Efficacy of Knowledge Distillation](https://mlsanity.com/paper/1910.01348/) (2019)
- [Knowledge Distillation Beyond Model Compression](https://mlsanity.com/paper/2007.01922/) (2020)

## Abstract (arXiv)

Knowledge distillation trains a smaller student to match the outputs of a larger teacher. Feature-based methods also align intermediate representations, but this extra constraint may affect students differently. We study this question on CIFAR-100 using a ResNet-50 teacher, a width-controlled CustomResNet family and MobileNetV2 as a cross-design comparison. For each student, we evaluate each feature method against a matched logit-KD run using the same teacher, optimizer settings, training schedule and seed. We repeat the main comparisons across multiple seeds. Logit KD improved every tested student over its scratch baseline. Attention Transfer showed no clear relationship with size inside the CustomResNet family, but its average effect was negative for that family and positive for MobileNetV2. FitNets was below logit KD in all 15 paired runs. Within the constant-depth width sweep, its gap increased for wider students, although the different-depth w=48 student did not follow this trend. Finally, the same auxiliary coefficient produced different gradient scales across students, showing that a fixed coefficient does not create a uniform training condition.