DeepSZ: A Novel Framework to Compress Deep Neural Networks by Using Error-Bounded Lossy Compression

Abstract

DNNs have been quickly and broadly exploited to improve the data analysis quality in many complex science and engineering applications. Today's DNNs are becoming deeper and wider because of increasing demand on the analysis quality and more and more complex applications to resolve. The wide and deep DNNs, however, require large amounts of resources, significantly restricting their utilization on resource-constrained systems. Although some network simplification methods have been proposed to address this issue, they suffer from either low compression ratios or high compression errors, which may introduce a costly retraining process for the target accuracy. In this paper, we propose DeepSZ: an accuracy-loss bounded neural network compression framework, which involves four key steps: network pruning, error bound assessment, optimization for error bound configuration, and compressed model generation, featuring a high compression ratio and low encoding time. The contribution is three-fold. (1) We develop an adaptive approach to select the feasible error bounds for each layer. (2) We build a model to estimate the overall loss of accuracy based on the accuracy degradation caused by individual decompressed layers. (3) We develop an efficient optimization algorithm to determine the best-fit configuration of error bounds in order to maximize the compression ratio under the user-set accuracy constraint. Experiments show that DeepSZ can compress AlexNet and VGG-16 on the ImageNet by a compression ratio of 46X and 116X, respectively, and compress LeNet-300-100 and LeNet-5 on the MNIST by a compression ratio of 57X and 56X, respectively, with only up to 0.3% loss of accuracy. Compared with other state-of-the-art methods, DeepSZ can improve the compression ratio by up to 1.43X, the DNN encoding performance by up to 4.0X (with four Nvidia Tesla V100 GPUs), and the decoding performance by up to 6.2X.

12 pages, 6 figures, accepted by HPDC'19

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Compressing Deep Convolutional Networks using Vector Quantization
• Predicting Parameters in Deep Learning
• Significantly Improving Lossy Compression for Scientific Data Sets Based on Multidimensional Prediction and Error-Controlled Quantization
• Provable Bounds for Learning Some Deep Representations
• SuperNeurons: Dynamic GPU Memory Management for Training Deep Neural Networks
• Weightless: Lossy Weight Encoding For Deep Neural Network Compression

Cited by in corpus (10)

• SDRBench: Scientific Data Reduction Benchmark for Lossy Compressors
• FT-CNN: Algorithm-Based Fault Tolerance for Convolutional Neural Networks
• cuSZ: An Efficient GPU-Based Error-Bounded Lossy Compression Framework for Scientific Data
• ClickTrain: Efficient and Accurate End-to-End Deep Learning Training via Fine-Grained Architecture-Preserving Pruning
• RTMobile: Beyond Real-Time Mobile Acceleration of RNNs for Speech Recognition
• Get More for Less in Decentralized Learning Systems
• SuperNeurons: FFT-based Gradient Sparsification in the Distributed Training of Deep Neural Networks
• COMET: A Novel Memory-Efficient Deep Learning Training Framework by Using Error-Bounded Lossy Compression
• TDC: Towards Extremely Efficient CNNs on GPUs via Hardware-Aware Tucker Decomposition
• Exploring Autoencoder-based Error-bounded Compression for Scientific Data