Ternary Spiking Neural Networks Enhanced by Complemented Neurons and Membrane Potential Aggregation

2026-01-22

AI Summary

Existing ternary spiking neurons suffer from information loss, vanishing temporal gradients, and irregular membrane potential distributions, which limit their biological plausibility and representational capacity. To address these issues, this work proposes the Complementary Ternary Spiking Neuron (CTSN) model, which incorporates a learnable complementary term to retain historical input information. Furthermore, a Temporal Membrane Potential Regularization (TMPR) training strategy is introduced, leveraging the time-varying evolution of membrane potentials to construct an auxiliary backpropagation pathway, thereby enhancing training stability and expressive power. CTSN also features an adaptive dynamic regulation mechanism that promotes neuronal heterogeneity. Experimental results demonstrate that the proposed approach significantly improves both performance and convergence stability of ternary spiking neural networks across multiple datasets.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Neuro-Symbolic Learning
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Spiking Neural Networks (SNNs) are promising energy-efficient models and powerful framworks of modeling neuron dynamics. However, existing binary spiking neurons exhibit limited biological plausibilities and low information capacity. Recently developed ternary spiking neuron possesses higher consistency with biological principles (i.e. excitation-inhibition balance mechanism). Despite of this, the ternary spiking neuron suffers from defects including iterative information loss, temporal gradient vanishing and irregular distributions of membrane potentials. To address these issues, we propose Complemented Ternary Spiking Neuron (CTSN), a novel ternary spiking neuron model that incorporates an learnable complemental term to store information from historical inputs. CTSN effectively improves the deficiencies of ternary spiking neuron, while the embedded learnable factors enable CTSN to adaptively adjust neuron dynamics, providing strong neural heterogeneity. Furthermore, based on the temporal evolution features of ternary spiking neurons'membrane potential distributions, we propose the Temporal Membrane Potential Regularization (TMPR) training method. TMPR introduces time-varying regularization strategy utilizing membrane potentials, furhter enhancing the training process by creating extra backpropagation paths. We validate our methods through extensive experiments on various datasets, demonstrating remarkable performance advances.

Problem

• Ternary Spiking Neuron
• Information Loss
• Gradient Vanishing
• Membrane Potential Distribution

Innovation

• Complemented Ternary Spiking Neuron
• Temporal Membrane Potential Regularization
• Spiking Neural Networks
• Membrane Potential Aggregation
• Neural Heterogeneity