Low-Rank+Sparse Tensor Compression for Neural Networks
This work addresses the challenge of reducing memory and compute for neural networks on edge devices, but it is incremental as it builds on existing compression techniques.
The paper tackles the problem of compressing neural networks for edge deployment by combining low-rank tensor decomposition with sparse pruning to leverage both coarse and fine structure, achieving improved compression over using either method alone on architectures like MobileNetv3 and EfficientNet.
Low-rank tensor compression has been proposed as a promising approach to reduce the memory and compute requirements of neural networks for their deployment on edge devices. Tensor compression reduces the number of parameters required to represent a neural network weight by assuming network weights possess a coarse higher-order structure. This coarse structure assumption has been applied to compress large neural networks such as VGG and ResNet. However modern state-of-the-art neural networks for computer vision tasks (i.e. MobileNet, EfficientNet) already assume a coarse factorized structure through depthwise separable convolutions, making pure tensor decomposition a less attractive approach. We propose to combine low-rank tensor decomposition with sparse pruning in order to take advantage of both coarse and fine structure for compression. We compress weights in SOTA architectures (MobileNetv3, EfficientNet, Vision Transformer) and compare this approach to sparse pruning and tensor decomposition alone.