Sub-network Multi-objective Evolutionary Algorithm for Filter Pruning
Li, Xuhua, Sun, Weize, Huang, Lei, Chen, Shaowu
–arXiv.org Artificial Intelligence
Filter pruning is a common method to achieve model compression and acceleration in deep neural networks (DNNs).Some research regarded filter pruning as a combinatorial optimization problem and thus used evolutionary algorithms (EA) to prune filters of DNNs. However, it is difficult to find a satisfactory compromise solution in a reasonable time due to the complexity of solution space searching. To solve this problem, we first formulate a multi-objective optimization problem based on a sub-network of the full model and propose a Sub-network Multiobjective Evolutionary Algorithm (SMOEA) for filter pruning. By progressively pruning the convolutional layers in groups, SMOEA can obtain a lightweight pruned result with better performance.Experiments on VGG-14 model for CIFAR-10 verify the effectiveness of the proposed SMOEA. Specifically, the accuracy of the pruned model with 16.56% parameters decreases by 0.28% only, which is better than the widely used popular filter pruning criteria.
arXiv.org Artificial Intelligence
Oct-22-2022
- Country:
- North America
- Canada > Quebec (0.05)
- United States
- Colorado (0.04)
- California (0.04)
- Europe > Spain
- Catalonia > Barcelona Province > Barcelona (0.04)
- Asia > China
- Guangdong Province > Shenzhen (0.06)
- North America
- Genre:
- Research Report (0.64)
- Technology: