Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning

TL;DR

This paper demonstrates that spiking neural networks with synaptic delay and temporal coding excel in graph reasoning tasks, offering energy-efficient and biologically plausible models that outperform traditional approaches.

Contribution

It introduces a novel SNN model leveraging synaptic delay and temporal coding for effective graph reasoning, with theoretical energy savings and empirical performance validation.

Findings

Achieves 20x energy savings over non-spiking models.

Effectively encodes relation properties via temporal coding.

Demonstrates strong performance on diverse graph reasoning tasks.

Abstract

Spiking neural networks (SNNs) are investigated as biologically inspired models of neural computation, distinguished by their computational capability and energy efficiency due to precise spiking times and sparse spikes with event-driven computation. A significant question is how SNNs can emulate human-like graph-based reasoning of concepts and relations, especially leveraging the temporal domain optimally. This paper reveals that SNNs, when amalgamated with synaptic delay and temporal coding, are proficient in executing (knowledge) graph reasoning. It is elucidated that spiking time can function as an additional dimension to encode relation properties via a neural-generalized path formulation. Empirical results highlight the efficacy of temporal delay in relation processing and showcase exemplary performance in diverse graph reasoning tasks. The spiking model is theoretically estimated to achieve $20\times$ energy savings compared to non-spiking counterparts, deepening insights into the capabilities and potential of biologically inspired SNNs for efficient reasoning. The code is available at https://github.com/pkuxmq/GRSNN.