# Utilizing Explainable AI for Quantization and Pruning of Deep Neural Networks

arXiv: https://arxiv.org/abs/2008.09072 · HTML: https://mlsanity.com/paper/2008.09072/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Aug 2020.

## Built on by (most cited first, 17 of 17)

- [Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement](https://mlsanity.com/paper/2203.08008/) (2022)
- [ECQx: Explainability-Driven Quantization for Low-Bit and Sparse DNNs](https://mlsanity.com/paper/2109.04236/) (2021)
- [Interpretations Steered Network Pruning via Amortized Inferred Saliency Maps](https://mlsanity.com/paper/2209.02869/) (2022)
- [XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approach](https://mlsanity.com/paper/2407.11771/) (2024)
- [Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability](https://mlsanity.com/paper/2108.01335/) (2021)
- [Utilizing Explainable AI for improving the Performance of Neural Networks](https://mlsanity.com/paper/2210.04686/) (2022)
- [Less is More: The Influence of Pruning on the Explainability of CNNs](https://mlsanity.com/paper/2302.08878/) (2023)
- [Hardware/Software Co-Design of RISC-V Extensions for Accelerating Sparse DNNs on FPGAs](https://mlsanity.com/paper/2504.19659/) (2025)
- [Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation](https://mlsanity.com/paper/2308.12053/) (2023)
- [Compressing Deep Neural Networks Using Explainable AI](https://mlsanity.com/paper/2507.05286/) (2025)
- [XAI-Enhanced Semantic Segmentation Models for Visual Quality Inspection](https://mlsanity.com/paper/2401.09900/) (2024)
- [Detection of Sensor-To-Sensor Variations using Explainable AI](https://mlsanity.com/paper/2306.10850/) (2023)
- [Explainable AI-Guided Efficient Approximate DNN Generation for Multi-Pod Systolic Arrays](https://mlsanity.com/paper/2503.16583/) (2025)
- [Relevance-driven Input Dropout: an Explanation-guided Regularization Technique](https://mlsanity.com/paper/2505.21595/) (2025)
- [Interpretability-Aware Pruning for Efficient Medical Image Analysis](https://mlsanity.com/paper/2507.08330/) (2025)
- [(Sometimes) Less is More: Mitigating the Complexity of Rule-based Representation for Interpretable Classification](https://mlsanity.com/paper/2509.22384/) (2025)
- [C-SWAP: Explainability-Aware Structured Pruning for Efficient Neural Networks Compression](https://mlsanity.com/paper/2510.18636/) (2025)

## Abstract (arXiv)

For many applications, utilizing DNNs (Deep Neural Networks) requires their implementation on a target architecture in an optimized manner concerning energy consumption, memory requirement, throughput, etc. DNN compression is used to reduce the memory footprint and complexity of a DNN before its deployment on hardware. Recent efforts to understand and explain AI (Artificial Intelligence) methods have led to a new research area, termed as explainable AI. Explainable AI methods allow us to understand better the inner working of DNNs, such as the importance of different neurons and features. The concepts from explainable AI provide an opportunity to improve DNN compression methods such as quantization and pruning in several ways that have not been sufficiently explored so far. In this paper, we utilize explainable AI methods: mainly DeepLIFT method. We use these methods for (1) pruning of DNNs; this includes structured and unstructured pruning of acCNN filters pruning as well as pruning weights of fully connected layers, (2) non-uniform quantization of DNN weights using clustering algorithm; this is also referred to as Weight Sharing, and (3) integer-based mixed-precision quantization; this is where each layer of a DNN may use a different number of integer bits. We use typical image classification datasets with common deep learning image classification models for evaluation. In all these three cases, we demonstrate significant improvements as well as new insights and opportunities from the use of explainable AI in DNN compression.