Weightless: Lossy Weight Encoding For Deep Neural Network Compression
This addresses memory constraints for deploying DNNs on resource-limited devices, offering a novel compression technique that complements existing methods.
The paper tackled the problem of large memory requirements in deep neural networks by introducing a lossy weight encoding scheme based on Bloomier filters, which compresses DNN weights by up to 496x with the same model accuracy, resulting in up to a 1.51x improvement over state-of-the-art methods.
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 496x with the same model accuracy. This results in up to a 1.51x improvement over the state-of-the-art.