# Are the High-weight Neurons the Important Ones in Image Classification Neural Networks?

arXiv: https://arxiv.org/abs/2607.25529 · HTML: https://mlsanity.com/paper/2607.25529/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 54 references that are in the map.
- First posted on arXiv 28 Jul 2026.

## Builds on (most cited first, 30 of 36)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [LLM-Pruner: On the Structural Pruning of Large Language Models](https://mlsanity.com/paper/2305.11627/) (2023)
- [Understanding Neural Networks Through Deep Visualization](https://mlsanity.com/paper/1506.06579/) (2015)
- [Understanding the Role of Individual Units in a Deep Neural Network](https://mlsanity.com/paper/2009.05041/) (2020)
- [Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models](https://mlsanity.com/paper/2301.04213/) (2023)
- [Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures](https://mlsanity.com/paper/1607.03250/) (2016)
- [DepGraph: Towards Any Structural Pruning](https://mlsanity.com/paper/2301.12900/) (2023)
- [A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations](https://mlsanity.com/paper/2308.06767/) (2023)
- [Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models](https://mlsanity.com/paper/2504.03624/) (2025)
- [On the importance of single directions for generalization](https://mlsanity.com/paper/1803.06959/) (2018)
- [Ablation Studies in Artificial Neural Networks](https://mlsanity.com/paper/1901.08644/) (2019)
- [Adversarial attacks and defenses in explainable artificial intelligence: A survey](https://mlsanity.com/paper/2306.06123/) (2023)
- [Pruning Filter in Filter](https://mlsanity.com/paper/2009.14410/) (2020)
- [Compression of Neural Machine Translation Models via Pruning](https://mlsanity.com/paper/1606.09274/) (2016)
- [Revisiting the Importance of Individual Units in CNNs via Ablation](https://mlsanity.com/paper/1806.02891/) (2018)
- [Towards Understanding Multi-Task Learning (Generalization) of LLMs via Detecting and Exploring Task-Specific Neurons](https://mlsanity.com/paper/2407.06488/) (2024)
- [Optimal ablation for interpretability](https://mlsanity.com/paper/2409.09951/) (2024)
- [Interspace Pruning: Using Adaptive Filter Representations to Improve Training of Sparse CNNs](https://mlsanity.com/paper/2203.07808/) (2022)
- [Comprehensive Survey of Model Compression and Speed up for Vision Transformers](https://mlsanity.com/paper/2404.10407/) (2024)
- [MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning](https://mlsanity.com/paper/2404.05621/) (2024)
- [Adversarial Training and Provable Robustness: A Tale of Two Objectives](https://mlsanity.com/paper/2008.06081/) (2020)
- [Quantifying Local Specialization in Deep Neural Networks](https://mlsanity.com/paper/2110.08058/) (2021)
- [Deep Model Compression based on the Training History](https://mlsanity.com/paper/2102.00160/) (2021)

## Abstract (arXiv)

As neural network models for image classification advance, neurons play critical roles in pruning, backdoor defense, and interpretability. Yet existing work lacks clarity on the weight-importance relationship. We address this with a neuron importance assessment method using three experiments: quantifying overlap between high-weight and accuracy-impacting neurons, analyzing high-weight neuron perturbation effects, and testing post-retraining accuracy after high-weight neuron ablation. Experiments on CIFAR-10 and Mini-ImageNet reveal key patterns. Overlap analysis shows top 10% high-weight neurons overlap with important ones by only about 25% at maximum, dropping further in subsequent intervals. Perturbation tests find top 10% high-weight neurons cause 45-80% accuracy degradation under certain operations compared to 3-7% for random perturbations, but a third of them show minimal impact. Ablation-retraining results show removing top 10% high-weight neurons leaves accuracy 10-20% below baseline with no recovery, while ablating top 0.1% allows near-full recovery. Notably, some low-weight intervals show 10-17% degradation when perturbed, comparable to mid-range high-weight neurons. These results confirm not all high-weight neurons are important: their importance is nonlinear. Low-weight neurons also contribute significantly. This challenges weight-importance equivalence, offering refined neuron role insights. It supports applications like encryption prioritizing critical high-weight neurons and pruning removing non-critical ones, advancing neural network analysis.