MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks

Ariel Gordon, Elad Eban, Ofir Nachum, Bo Chen, Hao Wu, Tien-Ju Yang, Edward Choi; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 1586-1595

Abstract


We present MorphNet, an approach to automate the design of neural network structures. MorphNet iteratively shrinks and expands a network, shrinking via a resource-weighted sparsifying regularizer on activations and expanding via a uniform multiplicative factor on all layers. In contrast to previous approaches, our method is scalable to large networks, adaptable to specific resource constraints (e.g. the number of floating-point operations per inference), and capable of increasing the network’s performance. When applied to standard network architectures on a wide variety of datasets, our approach discovers novel structures in each domain, obtaining higher performance while respecting the resource constraint.

Related Material


[pdf] [Supp] [arXiv]
[bibtex]
@InProceedings{Gordon_2018_CVPR,
author = {Gordon, Ariel and Eban, Elad and Nachum, Ofir and Chen, Bo and Wu, Hao and Yang, Tien-Ju and Choi, Edward},
title = {MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}