Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning

Mingqing Xiao, Yixin Zhu, Di He, Zhouchen Lin
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54341-54362, 2024.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-xiao24f, title = {Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning}, author = {Xiao, Mingqing and Zhu, Yixin and He, Di and Lin, Zhouchen}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {54341--54362}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/xiao24f/xiao24f.pdf}, url = {https://proceedings.mlr.press/v235/xiao24f.html}, 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.} }
Endnote
%0 Conference Paper %T Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning %A Mingqing Xiao %A Yixin Zhu %A Di He %A Zhouchen Lin %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-xiao24f %I PMLR %P 54341--54362 %U https://proceedings.mlr.press/v235/xiao24f.html %V 235 %X 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.
APA
Xiao, M., Zhu, Y., He, D. & Lin, Z.. (2024). Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:54341-54362 Available from https://proceedings.mlr.press/v235/xiao24f.html.

Related Material