Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

PruneTrain: Fast Neural Network Training by Dynamic Sparse Model Reconfiguration

About

State-of-the-art convolutional neural networks (CNNs) used in vision applications have large models with numerous weights. Training these models is very compute- and memory-resource intensive. Much research has been done on pruning or compressing these models to reduce the cost of inference, but little work has addressed the costs of training. We focus precisely on accelerating training. We propose PruneTrain, a cost-efficient mechanism that gradually reduces the training cost during training. PruneTrain uses a structured group-lasso regularization approach that drives the training optimization toward both high accuracy and small weight values. Small weights can then be periodically removed by reconfiguring the network model to a smaller one. By using a structured-pruning approach and additional reconfiguration techniques we introduce, the pruned model can still be efficiently processed on a GPU accelerator. Overall, PruneTrain achieves a reduction of 39% in the end-to-end training time of ResNet50 for ImageNet by reducing computation cost by 40% in FLOPs, memory accesses by 37% for memory bandwidth bound layers, and the inter-accelerator communication by 55%.

Sangkug Lym, Esha Choukse, Siavash Zangeneh, Wei Wen, Sujay Sanghavi, Mattan Erez• 2019

Related benchmarks

TaskDatasetResultRank
Image ClassificationCIFAR-10--
564
Image ClassificationOxford-IIIT Pets (test)
Mean Accuracy90.57
172
Image ClassificationFlowers-102 (test)
Top-1 Accuracy98.12
152
Image ClassificationStanford Dogs (test)
Top-1 Acc82.6
113
Image ClassificationCUB-200 (test)--
98
Image ClassificationGeneric Image Dataset 224x224
Peak Training Memory (MB)373.6
32
Showing 6 of 6 rows

Other info

Follow for update