# Sharing Leaky-Integrate-and-Fire Neurons for Memory-Efficient Spiking Neural Networks

arXiv: https://arxiv.org/abs/2305.18360 · HTML: https://mlsanity.com/paper/2305.18360/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2023.

## Built on by (most cited first, 5 of 5)

- [S-TLLR: STDP-inspired Temporal Local Learning Rule for Spiking Neural Networks](https://mlsanity.com/paper/2306.15220/) (2023)
- [Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity](https://mlsanity.com/paper/2506.12087/) (2025)
- [When In-memory Computing Meets Spiking Neural Networks -- A Perspective on Device-Circuit-System-and-Algorithm Co-design](https://mlsanity.com/paper/2408.12767/) (2024)
- [Toward Efficient Spiking Transformers: Synapse Pruning Meets Synergistic Learning-Based Compensation](https://mlsanity.com/paper/2508.01992/) (2025)
- [Beyond Low-Rank: Low-Rank Sparse Prompting via Spiking Neural Network and Prompt Factorization](https://mlsanity.com/paper/2606.01945/) (2026)

## Abstract (arXiv)

Spiking Neural Networks (SNNs) have gained increasing attention as energy-efficient neural networks owing to their binary and asynchronous computation. However, their non-linear activation, that is Leaky-Integrate-and-Fire (LIF) neuron, requires additional memory to store a membrane voltage to capture the temporal dynamics of spikes. Although the required memory cost for LIF neurons significantly increases as the input dimension goes larger, a technique to reduce memory for LIF neurons has not been explored so far. To address this, we propose a simple and effective solution, EfficientLIF-Net, which shares the LIF neurons across different layers and channels. Our EfficientLIF-Net achieves comparable accuracy with the standard SNNs while bringing up to ~4.3X forward memory efficiency and ~21.9X backward memory efficiency for LIF neurons. We conduct experiments on various datasets including CIFAR10, CIFAR100, TinyImageNet, ImageNet-100, and N-Caltech101. Furthermore, we show that our approach also offers advantages on Human Activity Recognition (HAR) datasets, which heavily rely on temporal information.