# Improving Feature Attribution through Input-specific Network Pruning

arXiv: https://arxiv.org/abs/1911.11081 · HTML: https://mlsanity.com/paper/1911.11081/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Nov 2019.

## Built on by (most cited first, 7 of 7)

- [Explainable Model-Agnostic Similarity and Confidence in Face Verification](https://mlsanity.com/paper/2211.13735/) (2022)
- [New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound](https://mlsanity.com/paper/2211.02912/) (2022)
- [SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation](https://mlsanity.com/paper/2411.01710/) (2024)
- [Less is More: The Influence of Pruning on the Explainability of CNNs](https://mlsanity.com/paper/2302.08878/) (2023)
- [sMRI-PatchNet: A novel explainable patch-based deep learning network for Alzheimer's disease diagnosis and discriminative atrophy localisation with Structural MRI](https://mlsanity.com/paper/2302.08967/) (2023)
- [Analyzing the Effects of Handling Data Imbalance on Learned Features from Medical Images by Looking Into the Models](https://mlsanity.com/paper/2204.01729/) (2022)
- [Smaller is Better: Enhancing Transparency in Vehicle AI Systems via Pruning](https://mlsanity.com/paper/2509.20148/) (2025)

## Abstract (arXiv)

Attributing the output of a neural network to the contribution of given input elements is a way of shedding light on the black-box nature of neural networks. Due to the complexity of current network architectures, current gradient-based attribution methods provide very noisy or coarse results. We propose to prune a neural network for a given single input to keep only neurons that highly contribute to the prediction. We show that by input-specific pruning, network gradients change from reflecting local (noisy) importance information to global importance. Our proposed method is efficient and generates fine-grained attribution maps. We further provide a theoretical justification of the pruning approach relating it to perturbations and validate it through a novel experimental setup. Our method is evaluated by multiple benchmarks: sanity checks, pixel perturbation, and Remove-and-Retrain (ROAR). These benchmarks evaluate the method from different perspectives and our method performs better than other methods across all evaluations.