Layer-adaptive Sparsity for the Magnitude-based Pruning

Jaeho Lee, Sejun Park, Sangwoo Mo, Sungsoo Ahn, Jinwoo Shin

Keywords: network pruning, layerwise sparsity, magnitude-based pruning

Abstract:

Recent discoveries on neural network pruning reveal that, with a carefully chosen layerwise sparsity, a simple magnitude-based pruning achieves state-of-the-art tradeoff between sparsity and performance. However, without a clear consensus on ``how to choose,'' the layerwise sparsities are mostly selected algorithm-by-algorithm, often resorting to handcrafted heuristics or an extensive hyperparameter search. To fill this gap, we propose a novel importance score for global pruning, coined layer-adaptive magnitude-based pruning (LAMP) score; the score is a rescaled version of weight magnitude that incorporates the model-level $\ell_2$ distortion incurred by pruning, and does not require any hyperparameter tuning or heavy computation.
Under various image classification setups, LAMP consistently outperforms popular existing schemes for layerwise sparsity selection.
Furthermore, we observe that LAMP continues to outperform baselines even in weight-rewinding setups, while the connectivity-oriented layerwise sparsity (the strongest baseline overall) performs worse than a simple global magnitude-based pruning in this case. Code: https://github.com/jaeho-lee/layer-adaptive-sparsity

One-sentence Summary: We propose LAMP, a general-purpose layerwise sparsity selection scheme for magnitude pruning.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Code: [ jaeho-lee/layer-adaptive-sparsity](https://github.com/jaeho-lee/layer-adaptive-sparsity)

Data: [CIFAR-10](https://paperswithcode.com/dataset/cifar-10), [CIFAR-100](https://paperswithcode.com/dataset/cifar-100), [SVHN](https://paperswithcode.com/dataset/svhn)