SPEAR: Structured Pruning for Spiking Neural Networks via Synaptic Operation Estimation and Reinforcement Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918082684911616 |
|---|---|
| author | Xie, Hui Liu, Yuhe Yang, Shaoqi Guo, Jinyang Guo, Yufei Ma, Yuqing Chen, Jiaxin Liu, Jiaheng Liu, Xianglong |
| author_facet | Xie, Hui Liu, Yuhe Yang, Shaoqi Guo, Jinyang Guo, Yufei Ma, Yuqing Chen, Jiaxin Liu, Jiaheng Liu, Xianglong |
| contents | While deep spiking neural networks (SNNs) demonstrate superior performance, their deployment on resource-constrained neuromorphic hardware still remains challenging. Network pruning offers a viable solution by reducing both parameters and synaptic operations (SynOps) to facilitate the edge deployment of SNNs, among which search-based pruning methods search for the SNNs structure after pruning. However, existing search-based methods fail to directly use SynOps as the constraint because it will dynamically change in the searching process, resulting in the final searched network violating the expected SynOps target. In this paper, we introduce a novel SNN pruning framework called SPEAR, which leverages reinforcement learning (RL) technique to directly use SynOps as the searching constraint. To avoid the violation of SynOps requirements, we first propose a SynOps prediction mechanism called LRE to accurately predict the final SynOps after search. Observing SynOps cannot be explicitly calculated and added to constrain the action in RL, we propose a novel reward called TAR to stabilize the searching. Extensive experiments show that our SPEAR framework can effectively compress SNN under specific SynOps constraint. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_02945 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SPEAR: Structured Pruning for Spiking Neural Networks via Synaptic Operation Estimation and Reinforcement Learning Xie, Hui Liu, Yuhe Yang, Shaoqi Guo, Jinyang Guo, Yufei Ma, Yuqing Chen, Jiaxin Liu, Jiaheng Liu, Xianglong Neural and Evolutionary Computing Artificial Intelligence Machine Learning While deep spiking neural networks (SNNs) demonstrate superior performance, their deployment on resource-constrained neuromorphic hardware still remains challenging. Network pruning offers a viable solution by reducing both parameters and synaptic operations (SynOps) to facilitate the edge deployment of SNNs, among which search-based pruning methods search for the SNNs structure after pruning. However, existing search-based methods fail to directly use SynOps as the constraint because it will dynamically change in the searching process, resulting in the final searched network violating the expected SynOps target. In this paper, we introduce a novel SNN pruning framework called SPEAR, which leverages reinforcement learning (RL) technique to directly use SynOps as the searching constraint. To avoid the violation of SynOps requirements, we first propose a SynOps prediction mechanism called LRE to accurately predict the final SynOps after search. Observing SynOps cannot be explicitly calculated and added to constrain the action in RL, we propose a novel reward called TAR to stabilize the searching. Extensive experiments show that our SPEAR framework can effectively compress SNN under specific SynOps constraint. |
| title | SPEAR: Structured Pruning for Spiking Neural Networks via Synaptic Operation Estimation and Reinforcement Learning |
| topic | Neural and Evolutionary Computing Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2507.02945 |