Shapley Pruning for Neural Network Compression
This work addresses efficient neural network deployment for AI practitioners, though it appears incremental by building on existing pruning concepts.
The authors tackled neural network compression by developing a Shapley value-based framework that connects existing pruning concepts, and their method achieved state-of-the-art compression results in broad experiments.
Neural network pruning is a rich field with a variety of approaches. In this work, we propose to connect the existing pruning concepts such as leave-one-out pruning and oracle pruning and develop them into a more general Shapley value-based framework that targets the compression of convolutional neural networks. To allow for practical applications in utilizing the Shapley value, this work presents the Shapley value approximations, and performs the comparative analysis in terms of cost-benefit utility for the neural network compression. The proposed ranks are evaluated against a new benchmark, Oracle rank, constructed based on oracle sets. The broad experiments show that the proposed normative ranking and its approximations show practical results, obtaining state-of-the-art network compression.