# Accuracy-Guaranteed Collaborative DNN Inference in Industrial IoT via Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2301.00130 · HTML: https://mlsanity.com/paper/2301.00130/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 31 references that are in the map.
- First posted on arXiv 31 Dec 2022.

## Builds on (most cited first, 11 of 11)

- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing](https://mlsanity.com/paper/1910.05316/) (2019)
- [Accelerated Primal-Dual Policy Optimization for Safe Reinforcement Learning](https://mlsanity.com/paper/1802.06480/) (2018)
- [Intelligence Beyond the Edge: Inference on Intermittent Embedded Systems](https://mlsanity.com/paper/1810.07751/) (2018)
- [Fast mmwave Beam Alignment via Correlated Bandit Learning](https://mlsanity.com/paper/1909.03313/) (2019)
- [Joint Service Caching and Task Offloading for Mobile Edge Computing in Dense Networks](https://mlsanity.com/paper/1801.05868/) (2018)
- [Content Popularity Prediction Towards Location-Aware Mobile Edge Caching](https://mlsanity.com/paper/1809.00232/) (2018)
- [Optimal Reliability in Energy Harvesting Industrial Wireless Sensor Networks](https://mlsanity.com/paper/1605.02068/) (2016)

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

- [Green Edge AI: A Contemporary Survey](https://mlsanity.com/paper/2312.00333/) (2023)
- [DNN Partitioning, Task Offloading, and Resource Allocation in Dynamic Vehicular Networks: A Lyapunov-Guided Diffusion-Based Reinforcement Learning Approach](https://mlsanity.com/paper/2406.06986/) (2024)
- [Holistic Network Virtualization and Pervasive Network Intelligence for 6G](https://mlsanity.com/paper/2301.00519/) (2023)
- [Enabling Resource-efficient AIoT System with Cross-level Optimization: A survey](https://mlsanity.com/paper/2309.15467/) (2023)
- [Towards Carbon-Neutral Edge Computing: Greening Edge AI by Harnessing Spot and Future Carbon Markets](https://mlsanity.com/paper/2304.11374/) (2023)
- [Two-Timescale Synchronization and Migration for Digital Twin Networks: A Multi-Agent Deep Reinforcement Learning Approach](https://mlsanity.com/paper/2409.01092/) (2024)
- [Energy-Efficient Split Learning for Fine-Tuning Large Language Models in Edge Networks](https://mlsanity.com/paper/2412.00090/) (2024)
- [Generative AI for Lyapunov Optimization Theory in UAV-based Low-Altitude Economy Networking](https://mlsanity.com/paper/2501.15928/) (2025)
- [Hardware-Aware DNN Compression for Homogeneous Edge Devices](https://mlsanity.com/paper/2501.15240/) (2025)
- [Collaborative Inference Acceleration with Non-Penetrative Tensor Partitioning](https://mlsanity.com/paper/2501.04489/) (2025)

## Abstract (arXiv)

Collaboration among industrial Internet of Things (IoT) devices and edge networks is essential to support computation-intensive deep neural network (DNN) inference services which require low delay and high accuracy. Sampling rate adaption which dynamically configures the sampling rates of industrial IoT devices according to network conditions, is the key in minimizing the service delay. In this paper, we investigate the collaborative DNN inference problem in industrial IoT networks. To capture the channel variation and task arrival randomness, we formulate the problem as a constrained Markov decision process (CMDP). Specifically, sampling rate adaption, inference task offloading and edge computing resource allocation are jointly considered to minimize the average service delay while guaranteeing the long-term accuracy requirements of different inference services. Since CMDP cannot be directly solved by general reinforcement learning (RL) algorithms due to the intractable long-term constraints, we first transform the CMDP into an MDP by leveraging the Lyapunov optimization technique. Then, a deep RL-based algorithm is proposed to solve the MDP. To expedite the training process, an optimization subroutine is embedded in the proposed algorithm to directly obtain the optimal edge computing resource allocation. Extensive simulation results are provided to demonstrate that the proposed RL-based algorithm can significantly reduce the average service delay while preserving long-term inference accuracy with a high probability.