# AdaDeep: A Usage-Driven, Automated Deep Model Compression Framework for Enabling Ubiquitous Intelligent Mobiles

arXiv: https://arxiv.org/abs/2006.04432 · HTML: https://mlsanity.com/paper/2006.04432/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jun 2020.

## Built on by (most cited first, 10 of 10)

- [Enabling Resource-efficient AIoT System with Cross-level Optimization: A survey](https://mlsanity.com/paper/2309.15467/) (2023)
- [Online Learning for Orchestration of Inference in Multi-User End-Edge-Cloud Networks](https://mlsanity.com/paper/2202.10541/) (2022)
- [MIMONet: Multi-Input Multi-Output On-Device Deep Learning](https://mlsanity.com/paper/2307.11962/) (2023)
- [Hybrid Learning for Orchestrating Deep Learning Inference in Multi-user Edge-cloud Networks](https://mlsanity.com/paper/2202.11098/) (2022)
- [UbiHR: Resource-efficient Long-range Heart Rate Sensing on Ubiquitous Devices](https://mlsanity.com/paper/2410.19279/) (2024)
- [AdaSpring: Context-adaptive and Runtime-evolutionary Deep Model Compression for Mobile Applications](https://mlsanity.com/paper/2101.11800/) (2021)
- [A Converting Autoencoder Toward Low-latency and Energy-efficient DNN Inference at the Edge](https://mlsanity.com/paper/2403.07036/) (2024)
- [AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices](https://mlsanity.com/paper/2412.00724/) (2024)
- [EncodeNet: A Framework for Boosting DNN Accuracy with Entropy-driven Generalized Converting Autoencoder](https://mlsanity.com/paper/2404.13770/) (2024)
- [AutoMCU: Feasibility-First MCU Neural Network Customization via LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2605.21560/) (2026)

## Abstract (arXiv)

Recent breakthroughs in Deep Neural Networks (DNNs) have fueled a tremendously growing demand for bringing DNN-powered intelligence into mobile platforms. While the potential of deploying DNNs on resource-constrained platforms has been demonstrated by DNN compression techniques, the current practice suffers from two limitations: 1) merely stand-alone compression schemes are investigated even though each compression technique only suit for certain types of DNN layers; and 2) mostly compression techniques are optimized for DNNs' inference accuracy, without explicitly considering other application-driven system performance (e.g., latency and energy cost) and the varying resource availability across platforms (e.g., storage and processing capability). To this end, we propose AdaDeep, a usage-driven, automated DNN compression framework for systematically exploring the desired trade-off between performance and resource constraints, from a holistic system level. Specifically, in a layer-wise manner, AdaDeep automatically selects the most suitable combination of compression techniques and the corresponding compression hyperparameters for a given DNN. Thorough evaluations on six datasets and across twelve devices demonstrate that AdaDeep can achieve up to 18.6× latency reduction, 9.8× energy-efficiency improvement, and 37.3× storage reduction in DNNs while incurring negligible accuracy loss. Furthermore, AdaDeep also uncovers multiple novel combinations of compression techniques.