# Activation-Energy Pruning for Spiking Neural Networks: Unsupervised Personalization via Spike-Count Saliency

arXiv: https://arxiv.org/abs/2609.26167 · HTML: https://mlsanity.com/paper/2609.26167/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 47 references that are in the map.
- First posted on arXiv 11 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [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)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [A Survey of Unsupervised Deep Domain Adaptation](https://mlsanity.com/paper/1812.02849/) (2018)
- [Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades](https://mlsanity.com/paper/1507.07629/) (2015)
- [Spikformer: When Spiking Neural Network Meets Transformer](https://mlsanity.com/paper/2209.15425/) (2022)
- [Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift](https://mlsanity.com/paper/2006.10963/) (2020)
- [Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting](https://mlsanity.com/paper/2202.11946/) (2022)
- [Pruning Neural Networks at Initialization: Why are We Missing the Mark?](https://mlsanity.com/paper/2009.08576/) (2020)
- [Salvaging Federated Learning by Local Adaptation](https://mlsanity.com/paper/2002.04758/) (2020)
- [Pruning of Deep Spiking Neural Networks through Gradient Rewiring](https://mlsanity.com/paper/2105.04916/) (2021)
- [Exploring Lottery Ticket Hypothesis in Spiking Neural Networks](https://mlsanity.com/paper/2207.01382/) (2022)
- [Unleashing the Potential of Spiking Neural Networks by Dynamic Confidence](https://mlsanity.com/paper/2303.10276/) (2023)
- [Bonsai: A Framework for Convolutional Neural Network Acceleration Using Criterion-Based Pruning](https://mlsanity.com/paper/2602.17145/) (2026)
- [Fine-Pruning: A Biologically Inspired Algorithm for Personalization of Machine Learning Models](https://mlsanity.com/paper/2602.18507/) (2026)

## Abstract (arXiv)

Activation-energy pruning -- removing weights whose product of magnitude and cumulative pre-synaptic spike count falls below a threshold -- was established as an effective unsupervised personalization strategy for conventional deep neural networks~citepBINGHAM2025101242. This paper asks what happens when the same criterion is applied to spiking neural networks (SNNs), where activation energy is not merely a useful heuristic but a literal physical quantity proportional to the metabolic cost of each synapse. The answer is surprising on three counts. First, gradient-based pruning methods that perform competitively on conventional networks (SNIP, GraSP, magnitude pruning) consistently underperform on SNNs, collapsing to near-chance accuracy by σ = 0.2 sparsity across all tested architectures and datasets. We trace this to a systematic incompatibility between surrogate-gradient saliency estimation and the binary spike-train representation, though we cannot rule out that alternative surrogate choices or hyperparameter settings might partially mitigate the effect. Second, activation-energy pruning applied to a neuromorphic benchmark improves over the source model at high sparsity (98.4 ± 0.4% vs. 97.2 ± 0.7% at σ = 0.8 on N-MNIST), a phenomenon with no counterpart in the conventional network setting. We interpret this result as consistent with experience-dependent cortical specialisation: removing connections active only for non-target classes may reduce cross-class interference and produce a cleaner target representation, though we note this is an interpretive analogy rather than a mechanistic demonstration.