# Mix-and-Match Pruning: Globally Guided Layer-Wise Sparsification of DNNs

arXiv: https://arxiv.org/abs/2603.20280 · HTML: https://mlsanity.com/paper/2603.20280/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 13 references that are in the map.
- First posted on arXiv 17 Mar 2026.

## Builds on (most cited first, 10 of 10)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [Picking Winning Tickets Before Training by Preserving Gradient Flow](https://mlsanity.com/paper/2002.07376/) (2020)
- [LPViT: Low-Power Semi-structured Pruning for Vision Transformers](https://mlsanity.com/paper/2407.02068/) (2024)
- [Exploration of Activation Fault Reliability in Quantized Systolic Array-Based DNN Accelerators](https://mlsanity.com/paper/2401.09509/) (2024)
- [HAWX: A Hardware-Aware FrameWork for Fast and Scalable ApproXimation of DNNs](https://mlsanity.com/paper/2602.16336/) (2026)
- [Sensitivity-Guided Framework for Pruned and Quantized Reservoir Computing Accelerators](https://mlsanity.com/paper/2603.08737/) (2026)

## Built on by (most cited first, 2 of 2)

- [SENTRY: Statistical Reliability Analysis of Vision Transformers Under Soft Errors](https://mlsanity.com/paper/2606.07620/) (2026)
- [HASA: Subnet Allocation for Compute-Constrained Model-Heterogeneous Federated Learning](https://mlsanity.com/paper/2606.07621/) (2026)

## Abstract (arXiv)

Deploying deep neural networks (DNNs) on edge devices requires strong compression with minimal accuracy loss. This paper introduces Mix-and-Match Pruning, a globally guided, layer-wise sparsification framework that leverages sensitivity scores and simple architectural rules to generate diverse, high-quality pruning configurations. The framework addresses a key limitation that different layers and architectures respond differently to pruning, making single-strategy approaches suboptimal. Mix-and-Match derives architecture-aware sparsity ranges, e.g., preserving normalization layers while pruning classifiers more aggressively, and systematically samples these ranges to produce ten strategies per sensitivity signal (magnitude, gradient, or their combination). This eliminates repeated pruning runs while offering deployment-ready accuracy-sparsity trade-offs. Experiments on CNNs and Vision Transformers demonstrate Pareto-optimal results, with Mix-and-Match reducing accuracy degradation on Swin-Tiny by 40% relative to standard single-criterion pruning. These findings show that coordinating existing pruning signals enables more reliable and efficient compressed models than introducing new criteria.