Layer-adaptive Structured Pruning Guided by Latency
This work addresses the need for efficient model deployment in resource-constrained environments, though it is incremental as it builds on existing pruning methods by incorporating hardware-aware latency optimization.
The paper tackles the problem of structured pruning for neural networks to improve inference speed by proposing SP-LAMP, a method that uses a global importance score and group knapsack solver under latency constraints, resulting in ResNet50/ResNet18 being 1.28x/8.45x faster with minimal accuracy changes on ImageNet and CIFAR10.
Structured pruning can simplify network architecture and improve inference speed. Combined with the underlying hardware and inference engine in which the final model is deployed, better results can be obtained by using latency collaborative loss function to guide network pruning together. Existing pruning methods that optimize latency have demonstrated leading performance, however, they often overlook the hardware features and connection in the network. To address this problem, we propose a global importance score SP-LAMP(Structured Pruning Layer-Adaptive Magnitude-based Pruning) by deriving a global importance score LAMP from unstructured pruning to structured pruning. In SP-LAMP, each layer includes a filter with an SP-LAMP score of 1, and the remaining filters are grouped. We utilize a group knapsack solver to maximize the SP-LAMP score under latency constraints. In addition, we improve the strategy of collect the latency to make it more accurate. In particular, for ResNet50/ResNet18 on ImageNet and CIFAR10, SP-LAMP is 1.28x/8.45x faster with +1.7%/-1.57% top-1 accuracy changed, respectively. Experimental results in ResNet56 on CIFAR10 demonstrate that our algorithm achieves lower latency compared to alternative approaches while ensuring accuracy and FLOPs.