# Adaptive Edge Offloading for Image Classification Under Rate Limit

arXiv: https://arxiv.org/abs/2208.00485 · HTML: https://mlsanity.com/paper/2208.00485/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 39 references that are in the map.
- First posted on arXiv 31 Jul 2022.

## Builds on (most cited first, 20 of 20)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [Rainbow: Combining Improvements in Deep Reinforcement Learning](https://mlsanity.com/paper/1710.02298/) (2017)
- [Distributed Deep Neural Networks over the Cloud, the Edge and End Devices](https://mlsanity.com/paper/1709.01921/) (2017)
- [SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud](https://mlsanity.com/paper/2008.06402/) (2020)
- [BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems](https://mlsanity.com/paper/1910.14315/) (2019)
- [JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Services](https://mlsanity.com/paper/1801.08618/) (2018)
- [AI Benchmark: All About Deep Learning on Smartphones in 2019](https://mlsanity.com/paper/1910.06663/) (2019)
- [BottleNet: A Deep Learning Architecture for Intelligent Mobile Cloud Computing Services](https://mlsanity.com/paper/1902.01000/) (2019)
- [IDK Cascades: Fast Deep Learning by Learning not to Overthink](https://mlsanity.com/paper/1706.00885/) (2017)
- [Optimized Computation Offloading Performance in Virtual Edge Computing Systems via Deep Reinforcement Learning](https://mlsanity.com/paper/1805.06146/) (2018)
- [EmBench: Quantifying Performance Variations of Deep Neural Networks across Modern Commodity Devices](https://mlsanity.com/paper/1905.07346/) (2019)
- [Neural Network Inference on Mobile SoCs](https://mlsanity.com/paper/1908.11450/) (2019)
- [Learning-Based Computation Offloading for IoT Devices with Energy Harvesting](https://mlsanity.com/paper/1712.08768/) (2017)
- [Real-Time Edge Classification: Optimal Offloading under Token Bucket Constraints](https://mlsanity.com/paper/2010.13737/) (2020)

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

- [Progressive Neural Compression for Adaptive Image Offloading under Timing Constraints](https://mlsanity.com/paper/2310.05306/) (2023)
- [Optimizing Edge Offloading Decisions for Object Detection](https://mlsanity.com/paper/2410.18919/) (2024)

## Abstract (arXiv)

This paper considers a setting where embedded devices are used to acquire and classify images. Because of limited computing capacity, embedded devices rely on a parsimonious classification model with uneven accuracy. When local classification is deemed inaccurate, devices can decide to offload the image to an edge server with a more accurate but resource-intensive model. Resource constraints, e.g., network bandwidth, however, require regulating such transmissions to avoid congestion and high latency. The paper investigates this offloading problem when transmissions regulation is through a token bucket, a mechanism commonly used for such purposes. The goal is to devise a lightweight, online offloading policy that optimizes an application-specific metric (e.g., classification accuracy) under the constraints of the token bucket. The paper develops a policy based on a Deep Q-Network (DQN), and demonstrates both its efficacy and the feasibility of its deployment on embedded devices. Of note is the fact that the policy can handle complex input patterns, including correlation in image arrivals and classification accuracy. The evaluation is carried out by performing image classification over a local testbed using synthetic traces generated from the ImageNet image classification benchmark. Implementation of this work is available at https://github.com/qiujiaming315/edgeml-dqn.