ClickTrain

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 Click-Train: an efficient and accurate end-to-end training and pruning framework for CNNs. Different from the existing pruning-duringtraining 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, Click-Train 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 2.3× 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. CCS CONCEPTS• Computing methodologies → Neural networks.

Towards efficient deep neural network inference and training for ubiquitous AI

“…RigL [90], ITOP [91], SET [104], DSR [89], and MEST [86], is provided in Tab. Three main sparsity schemes introduced in the area of network pruning consists of unstructured [105][106][107], structured [3,45,[108][109][110][111][112][113][114][115][116][117][118][119], and fine-grained structured pruning [120][121][122][123][124][125][126][127][128][129].…”