# CLIF: Complementary Leaky Integrate-and-Fire Neuron for Spiking Neural Networks

arXiv: https://arxiv.org/abs/2402.04663 · HTML: https://mlsanity.com/paper/2402.04663/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2024.

## Built on by (most cited first, 21 of 21)

- [Rethinking Spiking Neural Networks from an Ensemble Learning Perspective](https://mlsanity.com/paper/2502.14218/) (2025)
- [Towards Effective and Sparse Adversarial Attack on Spiking Neural Networks via Breaking Invisible Surrogate Gradients](https://mlsanity.com/paper/2503.03272/) (2025)
- [FAPNet: An Effective Frequency Adaptive Point-based Eye Tracker](https://mlsanity.com/paper/2406.03177/) (2024)
- [Improving Performance of Spike-based Deep Q-Learning using Ternary Neurons](https://mlsanity.com/paper/2506.03392/) (2025)
- [SpikingMamba: Towards Energy-Efficient Large Language Models via Knowledge Distillation from Mamba](https://mlsanity.com/paper/2510.04595/) (2025)
- [ClearSight: Human Vision-Inspired Solutions for Event-Based Motion Deblurring](https://mlsanity.com/paper/2501.15808/) (2025)
- [Edge Intelligence with Spiking Neural Networks](https://mlsanity.com/paper/2507.14069/) (2025)
- [AR-LIF: Adaptive reset leaky integrate-and-fire neuron for spiking neural networks](https://mlsanity.com/paper/2507.20746/) (2025)
- [Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers](https://mlsanity.com/paper/2510.07924/) (2025)
- [Rethinking SNN Online Training and Deployment: Gradient-Coherent Learning via Hybrid-Driven LIF Model](https://mlsanity.com/paper/2410.07547/) (2024)
- [DTA: Dual Temporal-channel-wise Attention for Spiking Neural Networks](https://mlsanity.com/paper/2503.10052/) (2025)
- [ILIF: Temporal Inhibitory Leaky Integrate-and-Fire Neuron for Overactivation in Spiking Neural Networks](https://mlsanity.com/paper/2505.10371/) (2025)
- [TDFormer: A Top-Down Attention-Controlled Spiking Transformer](https://mlsanity.com/paper/2505.15840/) (2025)
- [SPEAR: Structured Pruning for Spiking Neural Networks via Synaptic Operation Estimation and Reinforcement Learning](https://mlsanity.com/paper/2507.02945/) (2025)
- [Optimization of Low-Latency Spiking Neural Networks Utilizing Historical Dynamics of Refractory Periods](https://mlsanity.com/paper/2507.02960/) (2025)
- [Stabilizing Direct Training of Spiking Neural Networks: Membrane Potential Initialization and Threshold-robust Surrogate Gradient](https://mlsanity.com/paper/2511.08708/) (2025)
- [Stable Spike: Dual Consistency Optimization via Bitwise AND Operations for Spiking Neural Networks](https://mlsanity.com/paper/2603.11676/) (2026)
- [Neuronal Self-Adaptation Enhances Capacity and Robustness of Representation in Spiking Neural Networks](https://mlsanity.com/paper/2603.20687/) (2026)
- [Ge2mS-T: Multi-Dimensional Grouping for Ultra-High Energy Efficiency in Spiking Transformer](https://mlsanity.com/paper/2604.08894/) (2026)
- [DIMOS: Disentangling Instance-level Moving Object Segmentation](https://mlsanity.com/paper/2606.12826/) (2026)
- [Noisy group neurons with synchronous resetting for high-performance spiking neural networks](https://mlsanity.com/paper/2608.17394/) (2026)

## Abstract (arXiv)

Spiking neural networks (SNNs) are promising brain-inspired energy-efficient models. Compared to conventional deep Artificial Neural Networks (ANNs), SNNs exhibit superior efficiency and capability to process temporal information. However, it remains a challenge to train SNNs due to their undifferentiable spiking mechanism. The surrogate gradients method is commonly used to train SNNs, but often comes with an accuracy disadvantage over ANNs counterpart. We link the degraded accuracy to the vanishing of gradient on the temporal dimension through the analytical and experimental study of the training process of Leaky Integrate-and-Fire (LIF) Neuron-based SNNs. Moreover, we propose the Complementary Leaky Integrate-and-Fire (CLIF) Neuron. CLIF creates extra paths to facilitate the backpropagation in computing temporal gradient while keeping binary output. CLIF is hyperparameter-free and features broad applicability. Extensive experiments on a variety of datasets demonstrate CLIF's clear performance advantage over other neuron models. Furthermore, the CLIF's performance even slightly surpasses superior ANNs with identical network structure and training conditions. The code is available at https://github.com/HuuYuLong/Complementary-LIF.