BLK-REW: A Unified Block-based DNN Pruning Framework using Reweighted Regularization Method
Accelerating DNN execution on various resource-limited computing platforms has been a long-standing problem. Prior works utilize l1-based group lasso or dynamic regularization such as ADMM to perform structured pruning on DNN models to leverage the parallel computing architectures. However, both of the pruning dimensions and pruning methods lack universality, which leads to degraded performance and limited applicability. To solve the problem, we propose a new block-based pruning framework that comprises a general and flexible structured pruning dimension as well as a powerful and efficient reweighted regularization method. Our framework is universal, which can be applied to both CNNs and RNNs, implying complete support for the two major kinds of computation-intensive layers (i.e., CONV and FC layers). To complete all aspects of the pruning-for-acceleration task, we also integrate compiler-based code optimization into our framework that can perform DNN inference in a real-time manner. To the best of our knowledge, it is the first time that the weight pruning framework achieves universal coverage for both CNNs and RNNs with real-time mobile acceleration and no accuracy compromise.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Unified DNN Weight Compression Framework Using Reweighted Optimization Methods
To address the large model size and intensive computation requirement of deep neural networks (DNNs), weight pruning techniques have been proposed and generally fall into two categories, i.e., static regularization-based…
Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression
In this paper, we analyze two popular network compression techniques, i.e. filter pruning and low-rank decomposition, in a unified sense. By simply changing the way the sparsity regularization is enforced, filter pruning…
Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured Pruning
Pre-trained large-scale language models have increasingly demonstrated high accuracy on many natural language processing (NLP) tasks. However, the limited weight storage and computational speed on hardware platforms have…
Edge-computingKnowledge DistillationA Unified Framework for Soft Threshold Pruning
Soft threshold pruning is among the cutting-edge pruning methods with state-of-the-art performance. However, previous methods either perform aimless searching on the threshold scheduler or simply set the threshold traina…
compressed sensingSchedulingAlgorithm to Compilation Co-design: An Integrated View of Neural Network Sparsity
Reducing computation cost, inference latency, and memory footprint of neural networks are frequently cited as research motivations for pruning and sparsity. However, operationalizing those benefits and understanding the …
CPULanguage Modelling