Temporal Misalignment in ANN-SNN Conversion and its Mitigation via Probabilistic Spiking Neurons

Velibor Bojkovic, Xiaofeng Wu, Bin Gu
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4791-4822, 2025.

Abstract

Spiking Neural Networks (SNNs) offer a more energy-efficient alternative to Artificial Neural Networks (ANNs) by mimicking biological neural principles, establishing them as a promising approach to mitigate the increasing energy demands of large-scale neural models. However, fully harnessing the capabilities of SNNs remains challenging due to their discrete signal processing and temporal dynamics. ANN-SNN conversion has emerged as a practical approach, enabling SNNs to achieve competitive performance on complex machine learning tasks. In this work, we identify a phenomenon in the ANN-SNN conversion framework, termed temporal misalignment, in which random spike rearrangement across SNN layers leads to performance improvements. Based on this observation, we introduce biologically plausible two-phase probabilistic (TPP) spiking neurons, further enhancing the conversion process. We demonstrate the advantages of our proposed method both theoretically and empirically through comprehensive experiments on CIFAR-10/100, CIFAR10-DVS, and ImageNet across a variety of architectures, achieving state-of-the-art results.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-bojkovic25a, title = {Temporal Misalignment in {ANN}-{SNN} Conversion and its Mitigation via Probabilistic Spiking Neurons}, author = {Bojkovic, Velibor and Wu, Xiaofeng and Gu, Bin}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {4791--4822}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/bojkovic25a/bojkovic25a.pdf}, url = {https://proceedings.mlr.press/v267/bojkovic25a.html}, abstract = {Spiking Neural Networks (SNNs) offer a more energy-efficient alternative to Artificial Neural Networks (ANNs) by mimicking biological neural principles, establishing them as a promising approach to mitigate the increasing energy demands of large-scale neural models. However, fully harnessing the capabilities of SNNs remains challenging due to their discrete signal processing and temporal dynamics. ANN-SNN conversion has emerged as a practical approach, enabling SNNs to achieve competitive performance on complex machine learning tasks. In this work, we identify a phenomenon in the ANN-SNN conversion framework, termed temporal misalignment, in which random spike rearrangement across SNN layers leads to performance improvements. Based on this observation, we introduce biologically plausible two-phase probabilistic (TPP) spiking neurons, further enhancing the conversion process. We demonstrate the advantages of our proposed method both theoretically and empirically through comprehensive experiments on CIFAR-10/100, CIFAR10-DVS, and ImageNet across a variety of architectures, achieving state-of-the-art results.} }
Endnote
%0 Conference Paper %T Temporal Misalignment in ANN-SNN Conversion and its Mitigation via Probabilistic Spiking Neurons %A Velibor Bojkovic %A Xiaofeng Wu %A Bin Gu %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-bojkovic25a %I PMLR %P 4791--4822 %U https://proceedings.mlr.press/v267/bojkovic25a.html %V 267 %X Spiking Neural Networks (SNNs) offer a more energy-efficient alternative to Artificial Neural Networks (ANNs) by mimicking biological neural principles, establishing them as a promising approach to mitigate the increasing energy demands of large-scale neural models. However, fully harnessing the capabilities of SNNs remains challenging due to their discrete signal processing and temporal dynamics. ANN-SNN conversion has emerged as a practical approach, enabling SNNs to achieve competitive performance on complex machine learning tasks. In this work, we identify a phenomenon in the ANN-SNN conversion framework, termed temporal misalignment, in which random spike rearrangement across SNN layers leads to performance improvements. Based on this observation, we introduce biologically plausible two-phase probabilistic (TPP) spiking neurons, further enhancing the conversion process. We demonstrate the advantages of our proposed method both theoretically and empirically through comprehensive experiments on CIFAR-10/100, CIFAR10-DVS, and ImageNet across a variety of architectures, achieving state-of-the-art results.
APA
Bojkovic, V., Wu, X. & Gu, B.. (2025). Temporal Misalignment in ANN-SNN Conversion and its Mitigation via Probabilistic Spiking Neurons. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:4791-4822 Available from https://proceedings.mlr.press/v267/bojkovic25a.html.

Related Material