# Learning the Optimal Path and DNN Partition for Collaborative Edge Inference

arXiv: https://arxiv.org/abs/2410.01857 · HTML: https://mlsanity.com/paper/2410.01857/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 45 references that are in the map.
- First posted on arXiv 2 Oct 2024.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing](https://mlsanity.com/paper/1910.05316/) (2019)
- [Stochastic bandits robust to adversarial corruptions](https://mlsanity.com/paper/1803.09353/) (2018)
- [Better Algorithms for Stochastic Bandits with Adversarial Corruptions](https://mlsanity.com/paper/1902.08647/) (2019)
- [JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Services](https://mlsanity.com/paper/1801.08618/) (2018)
- [BottleNet: A Deep Learning Architecture for Intelligent Mobile Cloud Computing Services](https://mlsanity.com/paper/1902.01000/) (2019)
- [CoEdge: Cooperative DNN Inference with Adaptive Workload Partitioning over Heterogeneous Edge Devices](https://mlsanity.com/paper/2012.03257/) (2020)
- [Artificial Intelligence-Enabled Intelligent 6G Networks](https://mlsanity.com/paper/1912.05744/) (2019)
- [An Algorithm for Stochastic and Adversarial Bandits with Switching Costs](https://mlsanity.com/paper/2102.09864/) (2021)
- [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)
- [Joint Task Offloading and Resource Allocation for Multi-Server Mobile-Edge Computing Networks](https://mlsanity.com/paper/1705.00704/) (2017)
- [Better Best of Both Worlds Bounds for Bandits with Switching Costs](https://mlsanity.com/paper/2206.03098/) (2022)
- [Autodidactic Neurosurgeon: Collaborative Deep Inference for Mobile Edge Intelligence via Online Learning](https://mlsanity.com/paper/2102.02638/) (2021)
- [DistrEdge: Speeding up Convolutional Neural Network Inference on Distributed Edge Devices](https://mlsanity.com/paper/2202.01699/) (2022)
- [Joint Optimization of Radio and Computational Resources for Multicell Mobile-Edge Computing](https://mlsanity.com/paper/1412.8416/) (2014)
- [Service Capacity Enhanced Task Offloading and Resource Allocation in Multi-Server Edge Computing Environment](https://mlsanity.com/paper/1903.04709/) (2019)
- [Sequential Offloading for Distributed DNN Computation in Multiuser MEC Systems](https://mlsanity.com/paper/2203.01005/) (2022)

## Built on by (most cited first, 3 of 3)

- [Effect of Selection Format on LLM Performance](https://mlsanity.com/paper/2503.06926/) (2025)
- [Online LLM Selection via Constrained Bandits with Time-Varying Demand](https://mlsanity.com/paper/2606.17489/) (2026)
- [From Novice to Expert: Cost-Aware Bandits for Evolving Worker Performance in Crowdsensing](https://mlsanity.com/paper/2607.13546/) (2026)

## Abstract (arXiv)

Recent advancements in Deep Neural Networks (DNNs) have catalyzed the development of numerous intelligent mobile applications and services. However, they also introduce significant computational challenges for resource-constrained mobile devices. To address this, collaborative edge inference has been proposed. This method involves partitioning a DNN inference task into several subtasks and distributing these across multiple network nodes. Despite its potential, most current approaches presume known network parameters -- like node processing speeds and link transmission rates -- or rely on a fixed sequence of nodes for processing the DNN subtasks. In this paper, we tackle a more complex scenario where network parameters are unknown and must be learned, and multiple network paths are available for distributing inference tasks. Specifically, we explore the learning problem of selecting the optimal network path and assigning DNN layers to nodes along this path, considering potential security threats and the costs of switching paths. We begin by deriving structural insights from the DNN layer assignment with complete network information, which narrows down the decision space and provides crucial understanding of optimal assignments. We then cast the learning problem with incomplete network information as a novel adversarial group linear bandits problem with switching costs, featuring rewards generation through a combined stochastic and adversarial process. We introduce a new bandit algorithm, B-EXPUCB, which combines elements of the classical blocked EXP3 and LinUCB algorithms, and demonstrate its sublinear regret. Extensive simulations confirm B-EXPUCB's superior performance in learning for collaborative edge inference over existing algorithms.