ClickTrain: Efficient and Accurate End-to-End Deep Learning Training via Fine-Grained Architecture-Preserving Pruning

TL;DR

ClickTrain is a novel end-to-end CNN training and pruning framework that achieves higher accuracy and compression ratios efficiently, reducing training and pruning time without sacrificing model performance.

Contribution

It introduces a fine-grained, architecture-preserving pruning method with pattern-based importance estimation and compiler optimizations for improved CNN training and deployment.

Findings

Reduces end-to-end training and pruning time by up to 2.3X.

Achieves higher accuracy and compression ratio than existing methods.

Generates highly accurate, deployable CNN models without extra overhead.

Abstract

Convolutional neural networks (CNNs) are becoming increasingly deeper, wider, and non-linear because of the growing demand on prediction accuracy and analysis quality. The wide and deep CNNs, however, require a large amount of computing resources and processing time. Many previous works have studied model pruning to improve inference performance, but little work has been done for effectively reducing training cost. In this paper, we propose ClickTrain: an efficient and accurate end-to-end training and pruning framework for CNNs. Different from the existing pruning-during-training work, ClickTrain provides higher model accuracy and compression ratio via fine-grained architecture-preserving pruning. By leveraging pattern-based pruning with our proposed novel accurate weight importance estimation, dynamic pattern generation and selection, and compiler-assisted computation optimizations, ClickTrain generates highly accurate and fast pruned CNN models for direct deployment without any extra time overhead, compared with the baseline training. ClickTrain also reduces the end-to-end time cost of the pruning-after-training method by up to 2.3X with comparable accuracy and compression ratio. Moreover, compared with the state-of-the-art pruning-during-training approach, ClickTrain provides significant improvements both accuracy and compression ratio on the tested CNN models and datasets, under similar limited training time.