# Workload-Balanced Pruning for Sparse Spiking Neural Networks

arXiv: https://arxiv.org/abs/2302.06746 · HTML: https://mlsanity.com/paper/2302.06746/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Feb 2023.

## Built on by (most cited first, 15 of 15)

- [SpikeNAS: A Fast Memory-Aware Neural Architecture Search Framework for Spiking Neural Network-based Embedded AI Systems](https://mlsanity.com/paper/2402.11322/) (2024)
- [Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNN](https://mlsanity.com/paper/2403.03409/) (2024)
- [LoAS: Fully Temporal-Parallel Dataflow for Dual-Sparse Spiking Neural Networks](https://mlsanity.com/paper/2407.14073/) (2024)
- [FireFly-S: Exploiting Dual-Side Sparsity for Spiking Neural Networks Acceleration with Reconfigurable Spatial Architecture](https://mlsanity.com/paper/2408.15578/) (2024)
- [Activity Sparsity Complements Weight Sparsity for Efficient RNN Inference](https://mlsanity.com/paper/2311.07625/) (2023)
- [Weight Sparsity Complements Activity Sparsity in Neuromorphic Language Models](https://mlsanity.com/paper/2405.00433/) (2024)
- [Onboard Optimization and Learning: A Survey](https://mlsanity.com/paper/2505.08793/) (2025)
- [SpikeX: Exploring Accelerator Architecture and Network-Hardware Co-Optimization for Sparse Spiking Neural Networks](https://mlsanity.com/paper/2505.12292/) (2025)
- [SPARQ: Spiking Early-Exit Neural Networks for Energy-Efficient Edge AI](https://mlsanity.com/paper/2603.14380/) (2026)
- [Adversarially Robust Spiking Neural Networks with Sparse Connectivity](https://mlsanity.com/paper/2505.15833/) (2025)
- [SpikeSMOKE: Spiking Neural Networks for Monocular 3D Object Detection with Cross-Scale Gated Coding](https://mlsanity.com/paper/2506.07737/) (2025)
- [SPEAR: Structured Pruning for Spiking Neural Networks via Synaptic Operation Estimation and Reinforcement Learning](https://mlsanity.com/paper/2507.02945/) (2025)
- [MD-SNN: Membrane Potential-aware Distillation on Quantized Spiking Neural Network](https://mlsanity.com/paper/2512.04443/) (2025)
- [Surrogates, Spikes, and Sparsity: Performance Analysis and Characterization of SNN Hyperparameters on Hardware](https://mlsanity.com/paper/2603.24891/) (2026)
- [Resource-Efficient Pruning for Transformer via Low-Rank Importance Estimation](https://mlsanity.com/paper/2608.24973/) (2026)

## Abstract (arXiv)

Pruning for Spiking Neural Networks (SNNs) has emerged as a fundamental methodology for deploying deep SNNs on resource-constrained edge devices. Though the existing pruning methods can provide extremely high weight sparsity for deep SNNs, the high weight sparsity brings a workload imbalance problem. Specifically, the workload imbalance happens when a different number of non-zero weights are assigned to hardware units running in parallel. This results in low hardware utilization and thus imposes longer latency and higher energy costs. In preliminary experiments, we show that sparse SNNs (~98% weight sparsity) can suffer as low as ~59% utilization. To alleviate the workload imbalance problem, we propose u-Ticket, where we monitor and adjust the weight connections of the SNN during Lottery Ticket Hypothesis (LTH) based pruning, thus guaranteeing the final ticket gets optimal utilization when deployed onto the hardware. Experiments indicate that our u-Ticket can guarantee up to 100% hardware utilization, thus reducing up to 76.9% latency and 63.8% energy cost compared to the non-utilization-aware LTH method.