# Multi-Agent Collaborative Inference via DNN Decoupling: Intermediate Feature Compression and Edge Learning

arXiv: https://arxiv.org/abs/2205.11854 · HTML: https://mlsanity.com/paper/2205.11854/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 44 references that are in the map.
- First posted on arXiv 24 May 2022.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems](https://mlsanity.com/paper/1910.14315/) (2019)
- [BottleNet: A Deep Learning Architecture for Intelligent Mobile Cloud Computing Services](https://mlsanity.com/paper/1902.01000/) (2019)
- [Hybrid Actor-Critic Reinforcement Learning in Parameterized Action Space](https://mlsanity.com/paper/1903.01344/) (2019)
- [JALAD: Joint Accuracy- and Latency-Aware Deep Structure Decoupling for Edge-Cloud Execution](https://mlsanity.com/paper/1812.10027/) (2018)
- [Efficient Multi-User Computation Offloading for Mobile-Edge Cloud Computing](https://mlsanity.com/paper/1510.00888/) (2015)
- [Optimized Computation Offloading Performance in Virtual Edge Computing Systems via Deep Reinforcement Learning](https://mlsanity.com/paper/1805.06146/) (2018)
- [Improving Device-Edge Cooperative Inference of Deep Learning via 2-Step Pruning](https://mlsanity.com/paper/1903.03472/) (2019)
- [Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge](https://mlsanity.com/paper/1812.06426/) (2018)
- [Decentralized Computation Offloading for Multi-User Mobile Edge Computing: A Deep Reinforcement Learning Approach](https://mlsanity.com/paper/1812.07394/) (2018)
- [Guardians of the Deep Fog: Failure-Resilient DNN Inference from Edge to Cloud](https://mlsanity.com/paper/1909.00995/) (2019)
- [Stacked Auto Encoder Based Deep Reinforcement Learning for Online Resource Scheduling in Large-Scale MEC Networks](https://mlsanity.com/paper/2001.09223/) (2020)

## Built on by (most cited first, 12 of 12)

- [Green Edge AI: A Contemporary Survey](https://mlsanity.com/paper/2312.00333/) (2023)
- [DeViT: Decomposing Vision Transformers for Collaborative Inference in Edge Devices](https://mlsanity.com/paper/2309.05015/) (2023)
- [A Survey on Trustworthy Edge Intelligence: From Security and Reliability To Transparency and Sustainability](https://mlsanity.com/paper/2310.17944/) (2023)
- [Semantic Edge Computing and Semantic Communications in 6G Networks: A Unifying Survey and Research Challenges](https://mlsanity.com/paper/2411.18199/) (2024)
- [Edge-device Collaborative Computing for Multi-view Classification](https://mlsanity.com/paper/2409.15973/) (2024)
- [Energy-Efficient Power Control for Multiple-Task Split Inference in UAVs: A Tiny Learning-Based Approach](https://mlsanity.com/paper/2401.00445/) (2023)
- [CoFormer: Collaborating with Heterogeneous Edge Devices for Scalable Transformer Inference](https://mlsanity.com/paper/2508.20375/) (2025)
- [Integrated Communication and Control for Energy-Efficient UAV Swarms: A Multi-Agent Reinforcement Learning Approach](https://mlsanity.com/paper/2509.23905/) (2025)
- [BioEnvSense: A Human-Centred Security Framework for Preventing Behaviour-Driven Cyber Incidents](https://mlsanity.com/paper/2602.19410/) (2026)
- [Networking-Aware Energy Efficiency in Agentic AI Inference: A Survey](https://mlsanity.com/paper/2604.07857/) (2026)
- [Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs](https://mlsanity.com/paper/2607.23115/) (2026)
- [A Privacy Study of Sparse Collaborative Inference](https://mlsanity.com/paper/2608.16236/) (2026)

## Abstract (arXiv)

Recently, deploying deep neural network (DNN) models via collaborative inference, which splits a pre-trained model into two parts and executes them on user equipment (UE) and edge server respectively, becomes attractive. However, the large intermediate feature of DNN impedes flexible decoupling, and existing approaches either focus on the single UE scenario or simply define tasks considering the required CPU cycles, but ignore the indivisibility of a single DNN layer. In this paper, we study the multi-agent collaborative inference scenario, where a single edge server coordinates the inference of multiple UEs. Our goal is to achieve fast and energy-efficient inference for all UEs. To achieve this goal, we first design a lightweight autoencoder-based method to compress the large intermediate feature. Then we define tasks according to the inference overhead of DNNs and formulate the problem as a Markov decision process (MDP). Finally, we propose a multi-agent hybrid proximal policy optimization (MAHPPO) algorithm to solve the optimization problem with a hybrid action space. We conduct extensive experiments with different types of networks, and the results show that our method can reduce up to 56% of inference latency and save up to 72% of energy consumption.