# Compressing Representations for Embedded Deep Learning

arXiv: https://arxiv.org/abs/1911.10321 · HTML: https://mlsanity.com/paper/1911.10321/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2019.

## Built on by (most cited first, 2 of 2)

- [Single-Training Collaborative Object Detectors Adaptive to Bandwidth and Computation](https://mlsanity.com/paper/2105.00591/) (2021)
- [Slimmable Encoders for Flexible Split DNNs in Bandwidth and Resource Constrained IoT Systems](https://mlsanity.com/paper/2306.12691/) (2023)

## Abstract (arXiv)

Despite recent advances in architectures for mobile devices, deep learning computational requirements remains prohibitive for most embedded devices. To address that issue, we envision sharing the computational costs of inference between local devices and the cloud, taking advantage of the compression performed by the first layers of the networks to reduce communication costs. Inference in such distributed setting would allow new applications, but requires balancing a triple trade-off between computation cost, communication bandwidth, and model accuracy. We explore that trade-off by studying the compressibility of representations at different stages of MobileNetV2, showing those results agree with theoretical intuitions about deep learning, and that an optimal splitting layer for network can be found with a simple PCA-based compression scheme.