Multi-Objective Pruning for CNNs Using Genetic Algorithm
This work addresses the need for efficient CNN compression for applications in resource-constrained environments, but it is incremental as it applies an existing method (GA) to a known pruning task.
The paper tackles the problem of pruning convolutional neural networks (CNNs) by proposing a genetic algorithm (GA) for multi-objective optimization, achieving a 95.42% reduction in parameter size and 16× speedup in computation with minimal accuracy loss on the MNIST dataset.
In this work, we propose a heuristic genetic algorithm (GA) for pruning convolutional neural networks (CNNs) according to the multi-objective trade-off among error, computation and sparsity. In our experiments, we apply our approach to prune pre-trained LeNet across the MNIST dataset, which reduces 95.42% parameter size and achieves 16$\times$ speedups of convolutional layer computation with tiny accuracy loss by laying emphasis on sparsity and computation, respectively. Our empirical study suggests that GA is an alternative pruning approach for obtaining a competitive compression performance. Additionally, compared with state-of-the-art approaches, GA is capable of automatically pruning CNNs based on the multi-objective importance by a pre-defined fitness function.