Effective Sparsification of Neural Networks with Global Sparsity Constraint
This work addresses the challenge of efficiently reducing model size and inference time for deep neural networks in real-world deployments, offering an automated solution that avoids manual layer-wise tuning.
The paper tackles the problem of suboptimal performance in neural network weight pruning due to manual tuning of layer-specific pruning rates, proposing ProbMask, a method that uses probability as a global criterion under a sparsification constraint, resulting in up to 10% higher Top-1 accuracy compared to previous state-of-the-art methods, especially at high pruning rates.
Weight pruning is an effective technique to reduce the model size and inference time for deep neural networks in real-world deployments. However, since magnitudes and relative importance of weights are very different for different layers of a neural network, existing methods rely on either manual tuning or handcrafted heuristic rules to find appropriate pruning rates individually for each layer. This approach generally leads to suboptimal performance. In this paper, by directly working on the probability space, we propose an effective network sparsification method called {\it probabilistic masking} (ProbMask), which solves a natural sparsification formulation under global sparsity constraint. The key idea is to use probability as a global criterion for all layers to measure the weight importance. An appealing feature of ProbMask is that the amounts of weight redundancy can be learned automatically via our constraint and thus we avoid the problem of tuning pruning rates individually for different layers in a network. Extensive experimental results on CIFAR-10/100 and ImageNet demonstrate that our method is highly effective, and can outperform previous state-of-the-art methods by a significant margin, especially in the high pruning rate situation. Notably, the gap of Top-1 accuracy between our ProbMask and existing methods can be up to 10\%. As a by-product, we show ProbMask is also highly effective in identifying supermasks, which are subnetworks with high performance in a randomly weighted dense neural network.