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

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.

arXiv comment12 pages, 15 figures, 2 tables, published by ICS'21

References in corpus (8)

• A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers
• PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruning
• CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices
• SuperNeurons: Dynamic GPU Memory Management for Training Deep Neural Networks
• Balanced Sparsity for Efficient DNN Inference on GPU
• DeepSZ: A Novel Framework to Compress Deep Neural Networks by Using Error-Bounded Lossy Compression
• PruneTrain: Fast Neural Network Training by Dynamic Sparse Model Reconfiguration
• Towards Ultra-High Performance and Energy Efficiency of Deep Learning Systems: An Algorithm-Hardware Co-Optimization Framework

Cited by in corpus (1)

• TDC: Towards Extremely Efficient CNNs on GPUs via Hardware-Aware Tucker Decomposition