# DNAD: Differentiable Neural Architecture Distillation

arXiv: https://arxiv.org/abs/2504.20080 · HTML: https://mlsanity.com/paper/2504.20080/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 45 of its 82 references that are in the map.
- First posted on arXiv 25 Apr 2025.

## Builds on (most cited first, 30 of 45)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Channel Pruning for Accelerating Very Deep Neural Networks](https://mlsanity.com/paper/1707.06168/) (2017)
- [Learning Structured Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1608.03665/) (2016)
- [Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations](https://mlsanity.com/paper/1609.07061/) (2016)
- [AutoML: A Survey of the State-of-the-Art](https://mlsanity.com/paper/1908.00709/) (2019)
- [A Comprehensive Overhaul of Feature Distillation](https://mlsanity.com/paper/1904.01866/) (2019)
- [Paraphrasing Complex Network: Network Compression via Factor Transfer](https://mlsanity.com/paper/1802.04977/) (2018)
- [Searching for A Robust Neural Architecture in Four GPU Hours](https://mlsanity.com/paper/1910.04465/) (2019)
- [Neural Architecture Search with Bayesian Optimisation and Optimal Transport](https://mlsanity.com/paper/1802.07191/) (2018)
- [Neural Architecture Optimization](https://mlsanity.com/paper/1808.07233/) (2018)
- [Quantization Networks](https://mlsanity.com/paper/1911.09464/) (2019)
- [Cross-Layer Distillation with Semantic Calibration](https://mlsanity.com/paper/2012.03236/) (2020)
- [Cross-Image Relational Knowledge Distillation for Semantic Segmentation](https://mlsanity.com/paper/2204.06986/) (2022)
- [Curriculum Temperature for Knowledge Distillation](https://mlsanity.com/paper/2211.16231/) (2022)
- [Stabilizing Differentiable Architecture Search via Perturbation-based Regularization](https://mlsanity.com/paper/2002.05283/) (2020)
- [Blockwisely Supervised Neural Architecture Search with Knowledge Distillation](https://mlsanity.com/paper/1911.13053/) (2019)
- [CARS: Continuous Evolution for Efficient Neural Architecture Search](https://mlsanity.com/paper/1909.04977/) (2019)
- [NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search](https://mlsanity.com/paper/2007.10396/) (2020)
- [Heterogeneous Knowledge Distillation using Information Flow Modeling](https://mlsanity.com/paper/2005.00727/) (2020)
- [β-DARTS: Beta-Decay Regularization for Differentiable Architecture Search](https://mlsanity.com/paper/2203.01665/) (2022)

## Abstract (arXiv)

To meet the demand for designing efficient neural networks with appropriate trade-offs between model performance (e.g., classification accuracy) and computational complexity, the differentiable neural architecture distillation (DNAD) algorithm is developed based on two cores, namely search by deleting and search by imitating. Primarily, to derive neural architectures in a space where cells of the same type no longer share the same topology, the super-network progressive shrinking (SNPS) algorithm is developed based on the framework of differentiable architecture search (DARTS), i.e., search by deleting. Unlike conventional DARTS-based approaches which yield neural architectures with simple structures and derive only one architecture during the search procedure, SNPS is able to derive a Pareto-optimal set of architectures with flexible structures by forcing the dynamic super-network shrink from a dense structure to a sparse one progressively. Furthermore, since knowledge distillation (KD) has shown great effectiveness to train a compact network with the assistance of an over-parameterized model, we integrate SNPS with KD to formulate the DNAD algorithm, i.e., search by imitating. By minimizing behavioral differences between the super-network and teacher network, the over-fitting of one-level DARTS is avoided and well-performed neural architectures are derived. Experiments on CIFAR-10 and ImageNet classification tasks demonstrate that both SNPS and DNAD are able to derive a set of architectures which achieve similar or lower error rates with fewer parameters and FLOPs. Particularly, DNAD achieves the top-1 error rate of 23.7% on ImageNet classification with a model of 6.0M parameters and 598M FLOPs, which outperforms most DARTS-based methods.