Timezone: »

Sparse Training via Boosting Pruning Plasticity with Neuroregeneration
Shiwei Liu · Tianlong Chen · Xiaohan Chen · Zahra Atashgahi · Lu Yin · Huanyu Kou · Li Shen · Mykola Pechenizkiy · Zhangyang Wang · Decebal Constantin Mocanu

Fri Dec 10 08:30 AM -- 10:00 AM (PST) @

Works on lottery ticket hypothesis (LTH) and single-shot network pruning (SNIP) have raised a lot of attention currently on post-training pruning (iterative magnitude pruning), and before-training pruning (pruning at initialization). The former method suffers from an extremely large computation cost and the latter usually struggles with insufficient performance. In comparison, during-training pruning, a class of pruning methods that simultaneously enjoys the training/inference efficiency and the comparable performance, temporarily, has been less explored. To better understand during-training pruning, we quantitatively study the effect of pruning throughout training from the perspective of pruning plasticity (the ability of the pruned networks to recover the original performance). Pruning plasticity can help explain several other empirical observations about neural network pruning in literature. We further find that pruning plasticity can be substantially improved by injecting a brain-inspired mechanism called neuroregeneration, i.e., to regenerate the same number of connections as pruned. We design a novel gradual magnitude pruning (GMP) method, named gradual pruning with zero-cost neuroregeneration (GraNet), that advances state of the art. Perhaps most impressively, its sparse-to-sparse version for the first time boosts the sparse-to-sparse training performance over various dense-to-sparse methods with ResNet-50 on ImageNet without extending the training time. We release all codes in https://github.com/Shiweiliuiiiiiii/GraNet.

Author Information

Shiwei Liu (Netherlands)

I am a third-year Ph.D. student in the Data Mining Group, Department of Mathematics and Computer Science, Eindhoven University of Technology (TU/e). My current research topics are dynamic sparse training, sparse neural networks, pruning, the generalization of neural networks, etc. I am looking for a postdoc position in machine learning.

Tianlong Chen (Unversity of Texas at Austin)
Xiaohan Chen (The University of Texas at Austin)
Zahra Atashgahi (University of Twente)
Lu Yin (Eindhoven University of Technology)
Huanyu Kou (University of Leeds)
Li Shen (Tencent AI Lab)
Mykola Pechenizkiy (TU Eindhoven)
Zhangyang Wang (UT Austin)
Decebal Constantin Mocanu (Eindhoven University of Technology)

More from the Same Authors