# GraphEdge: Dynamic Graph Partition and Task Scheduling for GNNs Computing in Edge Network

arXiv: https://arxiv.org/abs/2504.15905 · HTML: https://mlsanity.com/paper/2504.15905/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 57 references that are in the map.
- First posted on arXiv 22 Apr 2025.

## Builds on (most cited first, 14 of 14)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Spectral Networks and Locally Connected Networks on Graphs](https://mlsanity.com/paper/1312.6203/) (2013)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs](https://mlsanity.com/paper/2010.05337/) (2020)
- [Reducing Communication in Graph Neural Network Training](https://mlsanity.com/paper/2005.03300/) (2020)
- [GNN at the Edge: Cost-Efficient Graph Neural Network Processing over Distributed Edge Servers](https://mlsanity.com/paper/2210.17281/) (2022)
- [Real-time Monitoring and Analysis of Track and Field Athletes Based on Edge Computing and Deep Reinforcement Learning Algorithm](https://mlsanity.com/paper/2411.06720/) (2024)
- [Deep Reinforcement Learning for Trajectory Path Planning and Distributed Inference in Resource-Constrained UAV Swarms](https://mlsanity.com/paper/2212.11201/) (2022)
- [Dynamic Semantic Compression for CNN Inference in Multi-access Edge Computing: A Graph Reinforcement Learning-based Autoencoder](https://mlsanity.com/paper/2401.12167/) (2024)
- [Dependent Task Offloading in Edge Computing Using GNN and Deep Reinforcement Learning](https://mlsanity.com/paper/2303.17100/) (2023)
- [COOL: A Conjoint Perspective on Spatio-Temporal Graph Neural Network for Traffic Forecasting](https://mlsanity.com/paper/2403.01091/) (2024)

## Built on by (most cited first, 2 of 2)

- [Breaking Obfuscation: Cluster-Aware Graph with LLM-Aided Recovery for Malicious JavaScript Detection](https://mlsanity.com/paper/2507.22447/) (2025)
- [FT-MoE: Sustainable-learning Mixture of Experts for Fault-Tolerant Computing](https://mlsanity.com/paper/2504.20446/) (2025)

## Abstract (arXiv)

With the exponential growth of Internet of Things (IoT) devices, edge computing (EC) is gradually playing an important role in providing cost-effective services. However, existing approaches struggle to perform well in graph-structured scenarios where user data is correlated, such as traffic flow prediction and social relationship recommender systems. In particular, graph neural network (GNN)-based approaches lead to expensive server communication cost. To address this problem, we propose GraphEdge, an efficient GNN-based EC architecture. It considers the EC system of GNN tasks, where there are associations between users and it needs to take into account the task data of its neighbors when processing the tasks of a user. Specifically, the architecture first perceives the user topology and represents their data associations as a graph layout at each time step. Then the graph layout is optimized by calling our proposed hierarchical traversal graph cut algorithm (HiCut), which cuts the graph layout into multiple weakly associated subgraphs based on the aggregation characteristics of GNN, and the communication cost between different subgraphs during GNN inference is minimized. Finally, based on the optimized graph layout, our proposed deep reinforcement learning (DRL) based graph offloading algorithm (DRLGO) is executed to obtain the optimal offloading strategy for the tasks of users, the offloading strategy is subgraph-based, it tries to offload user tasks in a subgraph to the same edge server as possible while minimizing the task processing time and energy consumption of the EC system. Experimental results show the good effectiveness and dynamic adaptation of our proposed architecture and it also performs well even in dynamic scenarios.