Efficient and Effective Time-Series Forecasting with Spiking Neural Networks

Changze Lv, Yansen Wang, Dongqi Han, Xiaoqing Zheng, Xuanjing Huang, Dongsheng Li
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33624-33637, 2024.

Abstract

Spiking neural networks (SNNs), inspired by the spiking behavior of biological neurons, provide a unique pathway for capturing the intricacies of temporal data. However, applying SNNs to time-series forecasting is challenging due to difficulties in effective temporal alignment, complexities in encoding processes, and the absence of standardized guidelines for model selection. In this paper, we propose a framework for SNNs in time-series forecasting tasks, leveraging the efficiency of spiking neurons in processing temporal information. Through a series of experiments, we demonstrate that our proposed SNN-based approaches achieve comparable or superior results to traditional time-series forecasting methods on diverse benchmarks with much less energy consumption. Furthermore, we conduct detailed analysis experiments to assess the SNN’s capacity to capture temporal dependencies within time-series data, offering valuable insights into its nuanced strengths and effectiveness in modeling the intricate dynamics of temporal data. Our study contributes to the expanding field of SNNs and offers a promising alternative for time-series forecasting tasks, presenting a pathway for the development of more biologically inspired and temporally aware forecasting models. Our code is available at https://github.com/microsoft/SeqSNN.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-lv24d, title = {Efficient and Effective Time-Series Forecasting with Spiking Neural Networks}, author = {Lv, Changze and Wang, Yansen and Han, Dongqi and Zheng, Xiaoqing and Huang, Xuanjing and Li, Dongsheng}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {33624--33637}, 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/lv24d/lv24d.pdf}, url = {https://proceedings.mlr.press/v235/lv24d.html}, abstract = {Spiking neural networks (SNNs), inspired by the spiking behavior of biological neurons, provide a unique pathway for capturing the intricacies of temporal data. However, applying SNNs to time-series forecasting is challenging due to difficulties in effective temporal alignment, complexities in encoding processes, and the absence of standardized guidelines for model selection. In this paper, we propose a framework for SNNs in time-series forecasting tasks, leveraging the efficiency of spiking neurons in processing temporal information. Through a series of experiments, we demonstrate that our proposed SNN-based approaches achieve comparable or superior results to traditional time-series forecasting methods on diverse benchmarks with much less energy consumption. Furthermore, we conduct detailed analysis experiments to assess the SNN’s capacity to capture temporal dependencies within time-series data, offering valuable insights into its nuanced strengths and effectiveness in modeling the intricate dynamics of temporal data. Our study contributes to the expanding field of SNNs and offers a promising alternative for time-series forecasting tasks, presenting a pathway for the development of more biologically inspired and temporally aware forecasting models. Our code is available at https://github.com/microsoft/SeqSNN.} }
Endnote
%0 Conference Paper %T Efficient and Effective Time-Series Forecasting with Spiking Neural Networks %A Changze Lv %A Yansen Wang %A Dongqi Han %A Xiaoqing Zheng %A Xuanjing Huang %A Dongsheng Li %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-lv24d %I PMLR %P 33624--33637 %U https://proceedings.mlr.press/v235/lv24d.html %V 235 %X Spiking neural networks (SNNs), inspired by the spiking behavior of biological neurons, provide a unique pathway for capturing the intricacies of temporal data. However, applying SNNs to time-series forecasting is challenging due to difficulties in effective temporal alignment, complexities in encoding processes, and the absence of standardized guidelines for model selection. In this paper, we propose a framework for SNNs in time-series forecasting tasks, leveraging the efficiency of spiking neurons in processing temporal information. Through a series of experiments, we demonstrate that our proposed SNN-based approaches achieve comparable or superior results to traditional time-series forecasting methods on diverse benchmarks with much less energy consumption. Furthermore, we conduct detailed analysis experiments to assess the SNN’s capacity to capture temporal dependencies within time-series data, offering valuable insights into its nuanced strengths and effectiveness in modeling the intricate dynamics of temporal data. Our study contributes to the expanding field of SNNs and offers a promising alternative for time-series forecasting tasks, presenting a pathway for the development of more biologically inspired and temporally aware forecasting models. Our code is available at https://github.com/microsoft/SeqSNN.
APA
Lv, C., Wang, Y., Han, D., Zheng, X., Huang, X. & Li, D.. (2024). Efficient and Effective Time-Series Forecasting with Spiking Neural Networks. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:33624-33637 Available from https://proceedings.mlr.press/v235/lv24d.html.

Related Material