arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2408.01534cs.LG
收藏

一种用于高效深度神经网络压缩的自适应 Tensor-Train 分解方法

An Adaptive Tensor-Train Decomposition Approach for Efficient Deep Neural Network Compression

Computational Science Research Center(计算科学研究中心);University of California Irvine(加州大学尔湾分校);University of California, Davis(加州大学戴维斯分校);Department of Electrical and Computer Engineering(电气与计算机工程系);Department of Mathematics(数学系);Department of Computer Science(计算机科学系);California State University Fullerton(加州州立大学富尔顿分校)

Shiyi Luo, Mingshuo Liu, Yifeng Yu, Shangping Ren, Yu Bai

AI总结:

针对张量分解中张量秩选择计算复杂度高的问题,提出一种基于LWIQ的自动预算感知秩选择方法,通过代理分类器评估各层重要性并自适应调整秩,显著提升了搜索效率并实现了良好的模型压缩效果。

摘要:

在模型压缩领域,为张量分解选择合适的秩对于平衡模型压缩率和效率至关重要。然而,这种选择无论是手动完成还是通过基于优化的自动方法完成,通常都会增加计算复杂度。手动秩选择缺乏效率和可扩展性,通常需要大量的试错,而基于优化的自动方法则显著增加了计算负担。为了解决这一问题,我们引入了一种新颖的、自动的且具备预算感知能力的秩选择方法,用于高效的模型压缩,该方法采用了 Layer-Wise Imprinting Quantitation (LWIQ)。LWIQ 通过集成一个代理分类器来量化神经网络中每一层的重要性。该分类器评估该层对整体模型性能的影响,从而允许对张量秩进行更明智的调整。此外,我们的方法包含一个缩放因子,以适应不同的计算预算约束。这种预算感知能力消除了在不同预算场景下重复重新计算秩的需要。在 CIFAR-10 数据集上的实验结果表明,与最先进的基于代理的自动张量秩选择方法相比,我们的 LWIQ 在秩搜索效率上提高了 63.2%,并且在 ResNet-56 模型上,模型大小减少了 3.2 倍,准确率仅下降了 0.86%。

英文摘要:

In the field of model compression, choosing an appropriate rank for tensor decomposition is pivotal for balancing model compression rate and efficiency. However, this selection, whether done manually or through optimization-based automatic methods, often increases computational complexity. Manual rank selection lacks efficiency and scalability, often requiring extensive trial-and-error, while optimization-based automatic methods significantly increase the computational burden. To address this, we introduce a novel, automatic, and budget-aware rank selection method for efficient model compression, which employs Layer-Wise Imprinting Quantitation (LWIQ). LWIQ quantifies each layer's significance within a neural network by integrating a proxy classifier. This classifier assesses the layer's impact on overall model performance, allowing for a more informed adjustment of tensor rank. Furthermore, our approach includes a scaling factor to cater to varying computational budget constraints. This budget awareness eliminates the need for repetitive rank recalculations for different budget scenarios. Experimental results on the CIFAR-10 dataset show that our LWIQ improved by 63.2% in rank search efficiency, and the accuracy only dropped by 0.86% with 3.2x less model size on the ResNet-56 model as compared to the state-of-the-art proxy-based automatic tensor rank selection method.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑