Abstract: We present a provable, sampling-based approach for generating compact Convolutional Neural Networks (CNNs) by identifying and removing redundant filters from an over-parameterized network. Our algorithm uses a small batch of input data points to assign a saliency score to each filter and constructs an importance sampling distribution where filters that highly affect the output are sampled with correspondingly high probability. In contrast to existing filter pruning approaches, our method is simultaneously data-informed, exhibits provable guarantees on the size and performance of the pruned network, and is widely applicable to varying network architectures and data sets. Our analytical bounds bridge the notions of compressibility and importance of network structures, which gives rise to a fully-automated procedure for identifying and preserving filters in layers that are essential to the network's performance. Our experimental evaluations on popular architectures and data sets show that our algorithm consistently generates sparser and more efficient models than those constructed by existing filter pruning approaches.

Similar Papers

A Signal Propagation Perspective for Pruning Neural Networks at Initialization
Namhoon Lee, Thalaiyasingam Ajanthan, Stephen Gould, Philip H. S. Torr,
Lookahead: A Far-sighted Alternative of Magnitude-based Pruning
Sejun Park, Jaeho Lee, Sangwoo Mo, Jinwoo Shin,
Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers
Junjie LIU, Zhe XU, Runbin SHI, Ray C. C. Cheung, Hayden K.H. So,