Paper Info
Title
Faster CNNs with Direct Sparse Convolutions and Guided Pruning
Abstract
Phenomenally successful in practical inference problems, convolutional neural networks (CNN) are widely deployed in mobile devices, data centers, and even supercomputers.The number of parameters needed in CNNs, however, are often large and undesirable. Consequently, various methods have been developed to prune a CNN once it is trained. Nevertheless, the resulting CNNs offer limited benefits. While pruning the fully connected layers reduces a CNNu0027s size considerably, it does not improve inference speed noticeably as the compute heavy parts lie in convolutions. Pruning CNNs in a way that increase inference speed often imposes specific sparsity structures, thus limiting the achievable sparsity levels.We present a method to realize simultaneously size economy and speed improvement while pruning CNNs. Paramount to our success is an efficient general sparse-with-dense matrixmultiplication implementation that is applicable to convolution of feature maps with kernels of arbitrary sparsity patterns. Complementing this, we developed a performance model that predicts sweet spots of sparsity levels for different layers and on different computer architectures. Together, these two allow us to demonstrate 3.1-7.3x convolution speedups over dense convolution in AlexNet, on Intel Atom, Xeon, and Xeon Phi processors, spanning the spectrum from mobile devices to supercomputers.
Year
Venue
Field
2017
international conference on learning representations
Inference,Convolution,Convolutional neural network,Xeon Phi,Computer science,Parallel computing,Mobile device,Artificial intelligence,Xeon,Matrix multiplication,Machine learning,Pruning
DocType
Citations 
PageRank 
Conference
14
0.62
References 
Authors
22
7
Name
Order
Citations
PageRank
Jongsoo Park11039.49
Sheng Li2159853.64
Wei Wen335318.09
Ping Tak Peter Tang422912.50
Hai Li52435208.37
Yiran Chen63344259.09
Pradeep K. Dubey73432292.69