Abstract
Spiking Neural Networks (SNNs) have recently emerged as a new generation of low-power deep neural networks, which is suitable to be implemented on low-power mobile/edge devices. As such devices have limited memory storage, neural pruning on SNNs has been widely explored in recent years. Most existing SNN pruning works focus on shallow SNNs (2–6 layers), however, deeper SNNs (\(\ge \)16 layers) are proposed by state-of-the-art SNN works, which is difficult to be compatible with the current SNN pruning work. To scale up a pruning technique towards deep SNNs, we investigate Lottery Ticket Hypothesis (LTH) which states that dense networks contain smaller subnetworks (i.e., winning tickets) that achieve comparable performance to the dense networks. Our studies on LTH reveal that the winning tickets consistently exist in deep SNNs across various datasets and architectures, providing up to \(97\%\) sparsity without huge performance degradation. However, the iterative searching process of LTH brings a huge training computational cost when combined with the multiple timesteps of SNNs. To alleviate such heavy searching cost, we propose Early-Time (ET) ticket where we find the important weight connectivity from a smaller number of timesteps. The proposed ET ticket can be seamlessly combined with a common pruning techniques for finding winning tickets, such as Iterative Magnitude Pruning (IMP) and Early-Bird (EB) tickets. Our experiment results show that the proposed ET ticket reduces search time by up to \(38\%\) compared to IMP or EB methods. Code is available at Github.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Akopyan, F., et al.: TrueNorth: design and tool flow of a 65 mw 1 million neuron programmable neurosynaptic chip. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 34(10), 1537–1557 (2015)
Bai, Y., Wang, H., Tao, Z., Li, K., Fu, Y.: Dual lottery ticket hypothesis. In: International Conference on Learning Representations (2022). https://openreview.net/forum?id=fOsN52jn25l
Bellec, G., Salaj, D., Subramoney, A., Legenstein, R., Maass, W.: Long short-term memory and learning-to-learn in networks of spiking neurons. In: Advances in Neural Information Processing Systems 31 (2018)
Brix, C., Bahar, P., Ney, H.: Successfully applying the stabilized lottery ticket hypothesis to the transformer architecture. ar**v preprint ar**v:2005.03454 (2020)
Burkholz, R., Laha, N., Mukherjee, R., Gotovos, A.: On the existence of universal lottery tickets. ar**v preprint ar**v:2111.11146 (2021)
Chen, G.K., Kumar, R., Sumbul, H.E., Knag, P.C., Krishnamurthy, R.K.: A 4096-neuron 1M-synapse 3.8-pJ/SOP spiking neural network with on-chip STDP learning and sparse weights in 10-nm finfet CMOS. IEEE J. Solid-State Circuits 54(4), 992–1002 (2018)
Chen, T., et al.: The lottery ticket hypothesis for pre-trained BERT networks. In: Advances in Neural Information Processing Systems, vol. 33, pp. 15834–15846 (2020)
Chen, T., et al.: Sparsity winning twice: better robust generalization from more efficient training. In: International Conference on Learning Representations (2022). https://openreview.net/forum?id=SYuJXrXq8tw
Chen, Y., Yu, Z., Fang, W., Huang, T., Tian, Y.: Pruning of deep spiking neural networks through gradient rewiring. ar**v preprint ar**v:2105.04916 (2021)
Chen, Y.H., Emer, J., Sze, V.: Eyeriss: a spatial architecture for energy-efficient dataflow for convolutional neural networks. ACM SIGARCH Comput. Archit. News 44(3), 367–379 (2016)
Christensen, D.V., et al.: 2022 roadmap on neuromorphic computing and engineering. Neuromorphic Computing and Engineering (2022)
Comsa, I.M., Fischbacher, T., Potempa, K., Gesmundo, A., Versari, L., Alakuijala, J.: Temporal coding in spiking neural networks with alpha synaptic function. In: ICASSP 2020–2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8529–8533. IEEE (2020)
Davies, M., et al.: Loihi: a neuromorphic manycore processor with on-chip learning. IEEE Micro 38(1), 82–99 (2018)
Deng, L., et al.: Comprehensive SNN compression using ADMM optimization and activity regularization. IEEE Trans. Neural Networks and Learn. Syst. (2021)
Deng, S., Li, Y., Zhang, S., Gu, S.: Temporal efficient training of spiking neural network via gradient re-weighting. In: International Conference on Learning Representations (2022., https://openreview.net/forum?id=_XNtisL32jv
Desai, S., Zhan, H., Aly, A.: Evaluating lottery tickets under distributional shifts. ar**v preprint ar**v:1910.12708 (2019)
Ding, J., Yu, Z., Tian, Y., Huang, T.: Optimal ann-snn conversion for fast and accurate inference in deep spiking neural networks. ar**v preprint ar**v:2105.11654 (2021)
Ding, S., Chen, T., Wang, Z.: Audio lottery: speech recognition made ultra-lightweight, noise-robust, and transferable. In: International Conference on Learning Representations (2022). https://openreview.net/forum?id=9Nk6AJkVYB
Fang, W., et al.: Spikingjelly (2020). https://github.com/fangwei123456/spikingjelly
Fang, W., Yu, Z., Chen, Y., Huang, T., Masquelier, T., Tian, Y.: Deep residual learning in spiking neural networks. Advances in Neural Information Processing Systems 34 (2021)
Frankle, J., Carbin, M.: The lottery ticket hypothesis: finding sparse, trainable neural networks. ar**v preprint ar**v:1803.03635 (2018)
Frankle, J., Dziugaite, G.K., Roy, D.M., Carbin, M.: Stabilizing the lottery ticket hypothesis. ar**v preprint ar**v:1903.01611 (2019)
Furber, S.B., Galluppi, F., Temple, S., Plana, L.A.: The spinnaker project. Proc. IEEE 102(5), 652–665 (2014)
Girish, S., Maiya, S.R., Gupta, K., Chen, H., Davis, L.S., Shrivastava, A.: The lottery ticket hypothesis for object recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 762–771 (2021)
Guo, W., Fouda, M.E., Yantir, H.E., Eltawil, A.M., Salama, K.N.: Unsupervised adaptive weight pruning for energy-efficient neuromorphic systems. Frontiers in Neuroscience p. 1189 (2020)
Han, S., et al.: Dsd: Dense-sparse-dense training for deep neural networks. ar**v preprint ar**v:1607.04381 (2016)
Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. Advances in neural information processing systems 28 (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. ar**v preprint ar**v:1502.03167 (2015)
Izhikevich, E.M.: Simple model of spiking neurons. IEEE Trans. Neural Networks 14(6), 1569–1572 (2003)
Kalibhat, N.M., Balaji, Y., Feizi, S.: Winning lottery tickets in deep generative models. ar**v preprint ar**v:2010.02350 (2020)
Kim, Y., Li, Y., Park, H., Venkatesha, Y., Panda, P.: Neural architecture search for spiking neural networks. ar**v preprint ar**v:2201.10355 (2022)
Kim, Y., Panda, P.: Revisiting batch normalization for training low-latency deep spiking neural networks from scratch. Frontiers in neuroscience, p. 1638 (2020)
Kim, Y., Panda, P.: Visual explanations from spiking neural networks using interspike intervals. Sci. Rep. 11, 19037 (2021). https://doi.org/10.1038/s41598-021-98448-0 (2021)
Kim, Y., Venkatesha, Y., Panda, P.: Privatesnn: privacy-preserving spiking neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 1192–1200 (2022)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)
Kundu, S., Pedram, M., Beerel, P.A.: Hire-snn: harnessing the inherent robustness of energy-efficient deep spiking neural networks by training with crafted input noise. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 5209–5218 (2021)
Ledinauskas, E., Ruseckas, J., Juršėnas, A., Buračas, G.: Training deep spiking neural networks. ar**v preprint ar**v:2006.04436 (2020)
Lee, C., Sarwar, S.S., Panda, P., Srinivasan, G., Roy, K.: Enabling spike-based backpropagation for training deep neural network architectures. Front. Neurosci. 14 (2020)
Lee, J.H., Delbruck, T., Pfeiffer, M.: Training deep spiking neural networks using backpropagation. Front. Neurosci. 10, 508 (2016)
Lee, N., Ajanthan, T., Torr, P.H.: Snip: Single-shot network pruning based on connection sensitivity. ar**v preprint ar**v:1810.02340 (2018)
Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. ar**v preprint ar**v:1608.08710 (2016)
Li, Y., Deng, S., Dong, X., Gong, R., Gu, S.: A free lunch from ann: towards efficient, accurate spiking neural networks calibration. ar**v preprint ar**v:2106.06984 (2021)
Li, Y., Deng, S., Dong, X., Gu, S.: Converting artificial neural networks to spiking neural networks via parameter calibration. ar**v preprint ar**v:2205.10121 (2022)
Li, Y., Guo, Y., Zhang, S., Deng, S., Hai, Y., Gu, S.: Differentiable spike: Rethinking gradient-descent for training spiking neural networks. Advances in Neural Information Processing Systems 34 (2021)
Liu, S., et al.: Deep ensembling with no overhead for either training or testing: the all-round blessings of dynamic sparsity. ar**v preprint ar**v:2106.14568 (2021)
Liu, Z., Sun, M., Zhou, T., Huang, G., Darrell, T.: Rethinking the value of network pruning. ar**v preprint ar**v:1810.05270 (2018)
Loshchilov, I., Hutter, F.: Sgdr: Stochastic gradient descent with warm restarts. ar**v preprint ar**v:1608.03983 (2016)
Martinelli, F., Dellaferrera, G., Mainar, P., Cernak, M.: Spiking neural networks trained with backpropagation for low power neuromorphic implementation of voice activity detection. In: ICASSP 2020–2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8544–8548. IEEE (2020)
Mehta, R.: Sparse transfer learning via winning lottery tickets. ar**v preprint ar**v:1905.07785 (2019)
Morcos, A., Yu, H., Paganini, M., Tian, Y.: One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers. In: Advances in Neural Information Processing Systems 32 (2019)
Mostafa, H.: Supervised learning based on temporal coding in spiking neural networks. IEEE Trans. Neural Networks Learn. Syst. 29(7), 3227–3235 (2017)
Movva, R., Zhao, J.Y.: Dissecting lottery ticket transformers: structural and behavioral study of sparse neural machine translation. ar**v preprint ar**v:2009.13270 (2020)
Neftci, E.O., Mostafa, H., Zenke, F.: Surrogate gradient learning in spiking neural networks. IEEE Signal Process. Mag. 36, 61–63 (2019)
Neftci, E.O., Pedroni, B.U., Joshi, S., Al-Shedivat, M., Cauwenberghs, G.: Stochastic synapses enable efficient brain-inspired learning machines. Front. Neurosci. 10, 241 (2016)
Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning (2011)
Orchard, G., et al.: Efficient neuromorphic signal processing with loihi 2. In: 2021 IEEE Workshop on Signal Processing Systems (SiPS), pp. 254–259. IEEE (2021)
Parashar, A., Rhu, M., Mukkara, A., Puglielli, A., Venkatesan, R., Khailany, B., Emer, J., Keckler, S.W., Dally, W.J.: Scnn: an accelerator for compressed-sparse convolutional neural networks. ACM SIGARCH Computer Architecture News 45(2), 27–40 (2017)
Paszke, A., et al.: Automatic differentiation in pytorch. In: NIPS-W (2017)
Rathi, N., Panda, P., Roy, K.: Stdp-based pruning of connections and weight quantization in spiking neural networks for energy-efficient recognition. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 38(4), 668–677 (2018)
Rathi, N., Roy, K.: Diet-SNN: a low-latency spiking neural network with direct input encoding and leakage and threshold optimization. IEEE Trans. Neural Networks Learn Syst. (2021)
Rathi, N., Srinivasan, G., Panda, P., Roy, K.: Enabling deep spiking neural networks with hybrid conversion and spike timing dependent backpropagation. ar**v preprint ar**v:2005.01807 (2020)
Roy, K., Jaiswal, A., Panda, P.: Towards spike-based machine intelligence with neuromorphic computing. Nature 575(7784), 607–617 (2019)
Schuman, C.D., Kulkarni, S.R., Parsa, M., Mitchell, J.P., Kay, B., et al.: Opportunities for neuromorphic computing algorithms and applications. Nature Comput. Sci. 2(1), 10–19 (2022)
Shi, Y., Nguyen, L., Oh, S., Liu, X., Kuzum, D.: A soft-pruning method applied during training of spiking neural networks for in-memory computing applications. Front. Neurosci. 13, 405 (2019)
Shrestha, S.B., Orchard, G.: Slayer: Spike layer error reassignment in time. ar**v preprint ar**v:1810.08646 (2018)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. ICLR (2015)
Venkatesha, Y., Kim, Y., Tassiulas, L., Panda, P.: Federated learning with spiking neural networks. ar**v preprint ar**v:2106.06579 (2021)
Vischer, M.A., Lange, R.T., Sprekeler, H.: On lottery tickets and minimal task representations in deep reinforcement learning. ar**v preprint ar**v:2105.01648 (2021)
Wang, C., Zhang, G., Grosse, R.: Picking winning tickets before training by preserving gradient flow. ar**v preprint ar**v:2002.07376 (2020)
Wen, W., Wu, C., Wang, Y., Chen, Y., Li, H.: Learning structured sparsity in deep neural networks. In: Advances in Neural Information Processing Systems 29 (2016)
Wu, H., et al.: Training spiking neural networks with accumulated spiking flow. ijo 1(1) (2021)
Wu, J., Xu, C., Zhou, D., Li, H., Tan, K.C.: Progressive tandem learning for pattern recognition with deep spiking neural networks. ar**v preprint ar**v:2007.01204 (2020)
Wu, Y., Deng, L., Li, G., Zhu, J., Shi, L.: Spatio-temporal backpropagation for training high-performance spiking neural networks. Front. Neurosci. 12, 331 (2018)
Wu, Y., Deng, L., Li, G., Zhu, J., **e, Y., Shi, L.: Direct training for spiking neural networks: Faster, larger, better. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 1311–1318 (2019)
Wu, Y., Zhao, R., Zhu, J., Chen, F., Xu, M., Li, G., Song, S., Deng, L., Wang, G., Zheng, H., et al.: Brain-inspired global-local learning incorporated with neuromorphic computing. Nat. Commun. 13(1), 1–14 (2022)
**ao, H., Rasul, K., Vollgraf, R.: Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. ar**v preprint ar**v:1708.07747 (2017)
Yao, M., Gao, H., Zhao, G., Wang, D., Lin, Y., Yang, Z., Li, G.: Temporal-wise attention spiking neural networks for event streams classification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 10221–10230 (2021)
Yin, R., Moitra, A., Bhattacharjee, A., Kim, Y., Panda, P.: Sata: Sparsity-aware training accelerator for spiking neural networks. ar**v preprint ar**v:2204.05422 (2022)
You, H., et al.: Drawing early-bird tickets: Towards more efficient training of deep networks. ar**v preprint ar**v:1909.11957 (2019)
Yu, H., Edunov, S., Tian, Y., Morcos, A.S.: Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP. ar**v preprint ar**v:1906.02768 (2019)
Zhang, Z., Chen, X., Chen, T., Wang, Z.: Efficient lottery ticket finding: less data is more. In: International Conference on Machine Learning, pp. 12380–12390. PMLR (2021)
Zheng, H., Wu, Y., Deng, L., Hu, Y., Li, G.: Going deeper with directly-trained larger spiking neural networks. ar**v preprint ar**v:2011.05280 (2020)
Zhou, H., Lan, J., Liu, R., Yosinski, J.: Deconstructing lottery tickets: Zeros, signs, and the supermask. In: Advances in Neural Information Processing Systems 32 (2019)
Acknowledgment
We would like to thank Anna Hambitzer for her helpful comments. This work was supported in part by C-BRIC, a JUMP center sponsored by DARPA and SRC, Google Research Scholar Award, the National Science Foundation (Grant#1947826), TII (Abu Dhabi) and the DARPA AI Exploration (AIE) program.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kim, Y., Li, Y., Park, H., Venkatesha, Y., Yin, R., Panda, P. (2022). Exploring Lottery Ticket Hypothesis in Spiking Neural Networks. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13672. Springer, Cham. https://doi.org/10.1007/978-3-031-19775-8_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-19775-8_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19774-1
Online ISBN: 978-3-031-19775-8
eBook Packages: Computer ScienceComputer Science (R0)