# Weightless: Lossy Weight Encoding For Deep Neural Network Compression

arXiv: https://arxiv.org/abs/1711.04686 · HTML: https://mlsanity.com/paper/1711.04686/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Nov 2017.

## Built on by (most cited first, 7 of 7)

- [Circa: Stochastic ReLUs for Private Deep Learning](https://mlsanity.com/paper/2106.08475/) (2021)
- [Neural Network Compression for Noisy Storage Devices](https://mlsanity.com/paper/2102.07725/) (2021)
- [Compacting Deep Neural Networks for Internet of Things: Methods and Applications](https://mlsanity.com/paper/2103.11083/) (2021)
- [MCNC: Manifold-Constrained Reparameterization for Neural Compression](https://mlsanity.com/paper/2406.19301/) (2024)
- [Tabula: Efficiently Computing Nonlinear Activation Functions for Secure Neural Network Inference](https://mlsanity.com/paper/2203.02833/) (2022)
- [PRANC: Pseudo RAndom Networks for Compacting deep models](https://mlsanity.com/paper/2206.08464/) (2022)
- [t-READi: Transformer-Powered Robust and Efficient Multimodal Inference for Autonomous Driving](https://mlsanity.com/paper/2410.09747/) (2024)

## Abstract (arXiv)

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.