LegoNet: Memory Footprint Reduction Through Block Weight Clustering

Abstract

As the need for neural network-based applications to become more accurate and powerful grows, so too does their size and memory footprint. With embedded devices, whose cache and RAM are limited, this growth hinders their ability to leverage state-of-the-art neural network architectures. In this work, we propose \textbf{LegoNet}, a compression technique that \textbf{constructs blocks of weights of the entire model regardless of layer type} and clusters these induced blocks. Using blocks instead of individual values to cluster the weights, we were able to compress ResNet-50 trained for Cifar-10 and ImageNet with only 32 4x4 blocks, compressing the memory footprint by over a factor of \textbf{64x without having to remove any weights} or changing the architecture and \textbf{no loss to accuracy}, nor retraining or any data, and show how to find an arrangement of 16 4x4 blocks that gives a compression ratio of \textbf{128x with less than 3\% accuracy loss}. This was all achieved with \textbf{no need for (re)training or fine-tuning}.

7 pages, 24 figures, published to IEEE DASC 2022 (20th year)

References in corpus (10)

• Knowledge Distillation: A Survey
• Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
• Compressing Deep Convolutional Networks using Vector Quantization
• Ternary Weight Networks
• Learned Step Size Quantization
• Deep $k$-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions
• And the Bit Goes Down: Revisiting the Quantization of Neural Networks
• An Overview of Neural Network Compression
• FleXOR: Trainable Fractional Quantization
• Structural Pruning in Deep Neural Networks: A Small-World Approach