# Optimal Model Placement and Online Model Splitting for Device-Edge Co-Inference arXiv: https://arxiv.org/abs/2105.13618 ยท HTML: https://mlsanity.com/paper/2105.13618/ ## Key facts - Cited by 19 papers in the map (data through 14 Oct 2026). - Builds on 12 of its 28 references that are in the map. - First posted on arXiv 28 May 2021. ## Builds on (most cited first, 12 of 12) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014) - [Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing](https://mlsanity.com/paper/1905.10083/) (2019) - [Event-based Vision meets Deep Learning on Steering Prediction for Self-driving Cars](https://mlsanity.com/paper/1804.01310/) (2018) - [BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems](https://mlsanity.com/paper/1910.14315/) (2019) - [Communication-Computation Trade-Off in Resource-Constrained Edge Inference](https://mlsanity.com/paper/2006.02166/) (2020) - [JALAD: Joint Accuracy- and Latency-Aware Deep Structure Decoupling for Edge-Cloud Execution](https://mlsanity.com/paper/1812.10027/) (2018) - [Edge-Host Partitioning of Deep Neural Networks with Feature Space Encoding for Resource-Constrained Internet-of-Things Platforms](https://mlsanity.com/paper/1802.03835/) (2018) - [Improving Device-Edge Cooperative Inference of Deep Learning via 2-Step Pruning](https://mlsanity.com/paper/1903.03472/) (2019) - [Optimizing AI Service Placement and Resource Allocation in Mobile Edge Intelligence Systems](https://mlsanity.com/paper/2011.05708/) (2020) - [Pricing-Driven Service Caching and Task Offloading in Mobile Edge Computing](https://mlsanity.com/paper/2011.02154/) (2020) - [Joint Optimization of Service Caching Placement and Computation Offloading in Mobile Edge Computing Systems](https://mlsanity.com/paper/1906.00711/) (2019) ## Built on by (most cited first, 19 of 19) - [Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networks](https://mlsanity.com/paper/2303.15991/) (2023) - [Task-Oriented Sensing, Computation, and Communication Integration for Multi-Device Edge AI](https://mlsanity.com/paper/2207.00969/) (2022) - [Accelerating Split Federated Learning over Wireless Communication Networks](https://mlsanity.com/paper/2310.15584/) (2023) - [Combined Federated and Split Learning in Edge Computing for Ubiquitous Intelligence in Internet of Things: State of the Art and Future Directions](https://mlsanity.com/paper/2207.09611/) (2022) - [The Larger the Merrier? Efficient Large AI Model Inference in Wireless Edge Networks](https://mlsanity.com/paper/2505.09214/) (2025) - [Efficient Multiuser AI Downloading via Reusable Knowledge Broadcasting](https://mlsanity.com/paper/2307.15316/) (2023) - [COMSPLIT: A Communication-Aware Split Learning Design for Heterogeneous IoT Platforms](https://mlsanity.com/paper/2410.19375/) (2024) - [Communication Efficient Cooperative Edge AI via Event-Triggered Computation Offloading](https://mlsanity.com/paper/2501.02001/) (2025) - [Privacy-Aware Joint DNN Model Deployment and Partitioning Optimization for Collaborative Edge Inference Services](https://mlsanity.com/paper/2502.16091/) (2025) - [Energy-Efficient Power Control for Multiple-Task Split Inference in UAVs: A Tiny Learning-Based Approach](https://mlsanity.com/paper/2401.00445/) (2023) - [Fast AI Model Partition for Split Learning over Edge Networks](https://mlsanity.com/paper/2507.01041/) (2025) - [CycleSL: Server-Client Cyclical Update Driven Scalable Split Learning](https://mlsanity.com/paper/2511.18611/) (2025) - [Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment](https://mlsanity.com/paper/2411.00838/) (2024) - [Transferable Deployment of Semantic Edge Inference Systems via Unsupervised Domain Adaption](https://mlsanity.com/paper/2504.11873/) (2025) - [Fine-Grained AI Model Caching and Downloading With Coordinated Multipoint Broadcasting in Multi-Cell Edge Networks](https://mlsanity.com/paper/2509.19341/) (2025) - [Channel-Adaptive Edge AI: Maximizing Inference Throughput by Adapting Computational Complexity to Channel States](https://mlsanity.com/paper/2603.03146/) (2026) - [Multi-SPIN: Multi-Access Speculative Inference for Cooperative Token Generation at the Edge](https://mlsanity.com/paper/2606.04581/) (2026) - [MANE: A Multi-Path Adaptive Network for Edge Onloading of Deep Neural Networks](https://mlsanity.com/paper/2609.14660/) (2026) - [TopoCompress: Topology Aware Token Compression Algorithm for Distributed Edge MoE Inference](https://mlsanity.com/paper/2609.26061/) (2026) ## Abstract (arXiv) Device-edge co-inference opens up new possibilities for resource-constrained wireless devices (WDs) to execute deep neural network (DNN)-based applications with heavy computation workloads. In particular, the WD executes the first few layers of the DNN and sends the intermediate features to the edge server that processes the remaining layers of the DNN. By adapting the model splitting decision, there exists a tradeoff between local computation cost and communication overhead. In practice, the DNN model is re-trained and updated periodically at the edge server. Once the DNN parameters are regenerated, part of the updated model must be placed at the WD to facilitate on-device inference. In this paper, we study the joint optimization of the model placement and online model splitting decisions to minimize the energy-and-time cost of device-edge co-inference in presence of wireless channel fading. The problem is challenging because the model placement and model splitting decisions are strongly coupled, while involving two different time scales. We first tackle online model splitting by formulating an optimal stopping problem, where the finite horizon of the problem is determined by the model placement decision. In addition to deriving the optimal model splitting rule based on backward induction, we further investigate a simple one-stage look-ahead rule, for which we are able to obtain analytical expressions of the model splitting decision. The analysis is useful for us to efficiently optimize the model placement decision in a larger time scale. In particular, we obtain a closed-form model placement solution for the fully-connected multilayer perceptron with equal neurons. Simulation results validate the superior performance of the joint optimal model placement and splitting with various DNN structures.