TL;DR
This paper introduces SPEAR, a reinforcement learning-based framework for structured pruning of spiking neural networks that ensures SynOps constraints are met, improving deployment efficiency on resource-limited hardware.
Contribution
SPEAR uniquely integrates SynOps prediction and a new reward mechanism to directly enforce SynOps constraints during SNN pruning, addressing limitations of previous search-based methods.
Findings
Effective compression of SNNs under SynOps constraints
SPEAR outperforms existing pruning methods in maintaining network performance
Demonstrates practical deployment benefits on neuromorphic hardware
Abstract
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…
Peer Reviews
Decision·ICLR 2026 Conference Withdrawn Submission
+ The paper is clearly written and well structured, making it easy to follow the methodology and contributions. + The work introduces SynOps as a constraint within the NAS process, which is straightforward.
- NAS encompasses various search paradigms, including RL-based, gradient-based, and evolutionary approaches. Why do the authors specifically adopt an RL-based framework for deriving the pruning strategy? A more detailed justification and comparison with alternative NAS strategies would strengthen the methodological motivation. - Although the paper empirically shows a linear correlation between pre-fine-tuning and post-fine-tuning SynOps, the proposed estimation technique lacks theoretical groun
1. SPEAR’s focus on SynOps aligns closely with energy efficiency on neuromorphic hardware, which is relevant to SNN training. 2. The combination of linear regression estimation and RL-based optimization is elegant and practical and demonstrates that linear estimation is sufficient and more stable than nonlinear approaches. 3. This paper is well-structured and clear written, with detailed explanation of each component and motivation.
1. These is a green rectangular on page 6 and 7. This should be corrected in the final version. 2. The linear relationship assumption between pre- and post-finetuning SynOps is empirically validated but lacks formal theoretical grounding. 3. Though not excessive, cost-benefit trade-offs for extremely large SNNs are unexplored.
Originality 1. The paper integrates SynOps constraints into structured SNN pruning using reinforcement learning. 2. The TAR reward formulation elegantly transforms hard resource constraints into soft penalties, enabling smooth optimization. Quality 1. The paper demonstrates technical rigor, with detailed methodology, theoretical motivation, and algorithmic clarity. 2. Extensive quantitative results across both static and neuromorphic datasets validate generalizability. 3. Ablation studies syste
1. Limited novelty in RL formulation: While the paper integrates reinforcement learning into SNN pruning, the use of DDPG and reward shaping is largely inspired by existing ANN pruning frameworks. The novelty lies mainly in the application to SynOps constraints rather than a fundamentally new RL algorithm. 2. Comparison limited to few baselines: The evaluation primarily compares against NetworkSlimming and SCA-based pruning, which provides a limited perspective. Including more recent and diverse
1.**Well-motivated problem**. The observation that SynOps change significantly and irregularly after finetuning is important for SNN deployment and distinguishes this work from ANN pruning methods. 2.**Practical and effective approach**. The LRE method, despite its simplicity, achieves strong performance with low computational overhead. The TAR design cleverly converts hard constraints to soft penalties, enabling smoother optimization.
1. **Limited theoretical foundation of LRE**: While a linear relationship is empirically observed, the paper does not investigate the underlying mechanism or the conditions under which it applies. Furthermore, using 500 samples to learn two parameters (W and b) appears inefficient and requires further clarification. 2. **Limited experimental comparison**: Although SPEAR primarily addresses search-based structured pruning, a more comprehensive comparison with design-based, as well as other searc
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
