- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper proposes TDAP, a post-training pruning framework for spiking neural networks. It evaluates weight importance by jointly modeling the temporal information of spikes and the predictive dependencies between channels. The method employs a learnable Temporal Firing Rate (TFR) module and a Channel Cross-Correlation Dependency (CCD) module to derive scores that are then fused via a geometric mean. This approach requires only a small amount of unlabeled calibration data and eliminates the need for fine-tuning the backbone network. Experiments were conducted on CIFAR-10, CIFAR-100, and DVS-CIFAR10.
Critical strengths
-
By simultaneously accounting for the importance of time steps and the lagged predictive relationships between channels, the method provides a valuable complement to traditional metrics based on weight magnitude or static activation.
-
The calibration cost is low, requiring only 128 unlabeled samples without the need for backbone fine-tuning.
Critical weaknesses
-
The experiments are limited to three relatively small-scale datasets and the Spiking ResNet-19 architecture. The study lacks evaluations on large-scale datasets (such as ImageNet) or spiking Transformer architectures.
-
The paper does not provide assessments of inference latency, memory footprint, or energy consumption, making it difficult to fully substantiate the value of deploying this method on existing computational hardware and frameworks.
-
There is existing research in this field [1][2][3], yet the paper lacks a systematic discussion of these works and appropriate experimental comparisons.
-
The proposed framework largely follows the "weight magnitude multiplied by channel-wise statistics" scoring paradigm established by Wanda. Consequently, its innovation is limited, and the necessity for the newly introduced design components is not sufficiently justified.
-
The source of the 128 calibration samples, their specific data partition, and the sampling strategy used are not clearly defined. Furthermore, it is not specified whether the calibration data is strictly independent of the evaluation data.
[1] Dynamic Spatio-Temporal Pruning for Efficient Spiking Neural Networks.
[2] QP-SNNs: Quantized and Pruned Spiking Neural Networks.
[3] Towards Energy Efficient Spiking Neural Networks: An Unstructured Pruning Framework.
Questions for authors
-
Please clarify the key differences between this work and existing SNN pruning studies.
-
Additionally, provide relevant experimental and theoretical comparisons and explain the advantages of your method.