# Fast AI Model Partition for Split Learning over Edge Networks

arXiv: https://arxiv.org/abs/2507.01041 · HTML: https://mlsanity.com/paper/2507.01041/

## Key facts

- Cited by 1 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 23 Jun 2025.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Distributed learning of deep neural network over multiple agents](https://mlsanity.com/paper/1810.06060/) (2018)
- [CondenseNet: An Efficient DenseNet using Learned Group Convolutions](https://mlsanity.com/paper/1711.09224/) (2017)
- [Resnet in Resnet: Generalizing Residual Architectures](https://mlsanity.com/paper/1603.08029/) (2016)
- [Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications](https://mlsanity.com/paper/2111.12444/) (2021)
- [Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networks](https://mlsanity.com/paper/2303.15991/) (2023)
- [Split Learning over Wireless Networks: Parallel Design and Resource Management](https://mlsanity.com/paper/2204.08119/) (2022)
- [Mobility-Aware Cluster Federated Learning in Hierarchical Wireless Networks](https://mlsanity.com/paper/2108.09103/) (2021)
- [Network-Aware Optimization of Distributed Learning for Fog Computing](https://mlsanity.com/paper/2004.08488/) (2020)
- [Optimal Model Placement and Online Model Splitting for Device-Edge Co-Inference](https://mlsanity.com/paper/2105.13618/) (2021)
- [Accelerating Split Federated Learning over Wireless Communication Networks](https://mlsanity.com/paper/2310.15584/) (2023)
- [Holistic Network Virtualization and Pervasive Network Intelligence for 6G](https://mlsanity.com/paper/2301.00519/) (2023)
- [An Efficient Privacy-aware Split Learning Framework for Satellite Communications](https://mlsanity.com/paper/2409.08538/) (2024)
- [The Impact of Cut Layer Selection in Split Federated Learning](https://mlsanity.com/paper/2412.15536/) (2024)
- [COMSPLIT: A Communication-Aware Split Learning Design for Heterogeneous IoT Platforms](https://mlsanity.com/paper/2410.19375/) (2024)
- [Training Latency Minimization for Model-Splitting Allowed Federated Edge Learning](https://mlsanity.com/paper/2307.11532/) (2023)
- [Performance Analysis for Hybrid Sub-6GHz-mmWave-THz Networks with Downlink and Uplink Decoupled Cell Association](https://mlsanity.com/paper/2308.05842/) (2023)

## Built on by (most cited first, 1 of 1)

- [AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence](https://mlsanity.com/paper/2607.16562/) (2026)

## Abstract (arXiv)

Split learning (SL) is a distributed learning paradigm that can enable computation-intensive artificial intelligence (AI) applications by partitioning AI models between mobile devices and edge servers. %fully utilizing distributed computing resources for computation-intensive mobile intelligence applications. However, the model partitioning problem in SL becomes challenging due to the diverse and complex architectures of AI models. In this paper, we formulate an optimal model partitioning problem to minimize training delay in SL. To solve the problem, we represent an arbitrary AI model as a directed acyclic graph (DAG), where the model's layers and inter-layer connections are mapped to vertices and edges, and training delays are captured as edge weights. Then, we propose a general model partitioning algorithm by transforming the problem into a minimum textits-t cut problem on the DAG. Theoretical analysis shows that the two problems are equivalent, such that the optimal model partition can be obtained via a maximum-flow method. Furthermore, taking AI models with block structures into consideration, we design a low-complexity block-wise model partitioning algorithm to determine the optimal model partition. Specifically, the algorithm simplifies the DAG by abstracting each block (i.e., a repeating component comprising multiple layers in an AI model) into a single vertex. Extensive experimental results on a hardware testbed equipped with NVIDIA Jetson devices demonstrate that the proposed solution can reduce algorithm running time by up to 13.0× and training delay by up to 38.95%, compared to state-of-the-art baselines.