Weightless: Lossy weight encoding for deep neural network compression

Brandon Reagen, Udit Gupta, Robert Adolf, Michael Mitzenmacher, Alexander Rush, Gu-Yeon Wei, David Brooks

TL;DR: We propose a new way to compress neural networks using probabilistic data structures.

Abstract: The large memory requirements of deep neural networks limit their deployment and adoption on many devices. Model compression methods effectively reduce the memory requirements of these models, usually through applying transformations such as weight pruning or quantization. In this paper, we present a novel scheme for lossy weight encoding which complements conventional compression techniques. The encoding is based on the Bloomier filter, a probabilistic data structure that can save space at the cost of introducing random errors. Leveraging the ability of neural networks to tolerate these imperfections and by re-training around the errors, the proposed technique, Weightless, can compress DNN weights by up to 496× with the same model accuracy. This results in up to a 1.51× improvement over the state-of-the-art.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:1711.04686/code)