# GCoDE: Efficient Device-Edge Co-Inference for GNNs via Architecture-Mapping Co-Search

arXiv: https://arxiv.org/abs/2512.11856 · HTML: https://mlsanity.com/paper/2512.11856/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 39 references that are in the map.
- First posted on arXiv 5 Dec 2025.

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

- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud](https://mlsanity.com/paper/2003.01251/) (2020)
- [Evaluating the Search Phase of Neural Architecture Search](https://mlsanity.com/paper/1902.08142/) (2019)
- [Machine Learning at the Network Edge: A Survey](https://mlsanity.com/paper/1908.00080/) (2019)
- [Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks](https://mlsanity.com/paper/2004.13826/) (2020)
- [Rethinking Graph Neural Architecture Search from Message-passing](https://mlsanity.com/paper/2103.14282/) (2021)
- [A Survey on Collaborative DNN Inference for Edge Intelligence](https://mlsanity.com/paper/2207.07812/) (2022)
- [Characterizing and Understanding GCNs on GPU](https://mlsanity.com/paper/2001.10160/) (2020)
- [Branchy-GNN: a Device-Edge Co-Inference Framework for Efficient Point Cloud Processing](https://mlsanity.com/paper/2011.02422/) (2020)
- [The Larger The Fairer? Small Neural Networks Can Achieve Fairness for Edge Devices](https://mlsanity.com/paper/2202.11317/) (2022)
- [Towards Efficient Graph Convolutional Networks for Point Cloud Handling](https://mlsanity.com/paper/2104.05706/) (2021)
- [Hardware-Aware Graph Neural Network Automated Design for Edge Computing Platforms](https://mlsanity.com/paper/2303.10875/) (2023)
- [Towards Efficient Point Cloud Graph Neural Networks Through Architectural Simplification](https://mlsanity.com/paper/2108.06317/) (2021)
- [MaGNAS: A Mapping-Aware Graph Neural Architecture Search Framework for Heterogeneous MPSoC Deployment](https://mlsanity.com/paper/2307.08065/) (2023)
- [Lattice-based Improvements for Voice Triggering Using Graph Neural Networks](https://mlsanity.com/paper/2001.10822/) (2020)
- [SUGAR: Efficient Subgraph-level Training via Resource-aware Graph Partitioning](https://mlsanity.com/paper/2202.00075/) (2022)
- [LENS: Layer Distribution Enabled Neural Architecture Search in Edge-Cloud Hierarchies](https://mlsanity.com/paper/2107.09309/) (2021)
- [Roulette: A Semantic Privacy-Preserving Device-Edge Collaborative Inference Framework for Deep Learning Classification Tasks](https://mlsanity.com/paper/2309.02820/) (2023)
- [GraNNite: Enabling High-Performance Execution of Graph Neural Networks on Resource-Constrained Neural Processing Units](https://mlsanity.com/paper/2502.06921/) (2025)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have emerged as the state-of-the-art graph learning method. However, achieving efficient GNN inference on edge devices poses significant challenges, limiting their application in real-world edge scenarios. This is due to the high computational cost of GNNs and limited hardware resources on edge devices, which prevent GNN inference from meeting real-time and energy requirements. As an emerging paradigm, device-edge co-inference shows potential for improving inference efficiency and reducing energy consumption on edge devices. Despite its potential, research on GNN device-edge co-inference remains scarce, and our findings show that traditional model partitioning methods are ineffective for GNNs. To address this, we propose GCoDE, the first automatic framework for GNN architecture-mapping Co-design and deployment on Device-Edge hierarchies. By abstracting the device communication process into an explicit operation, GCoDE fuses the architecture and mapping scheme in a unified design space for joint optimization. Additionally, GCoDE's system performance awareness enables effective evaluation of architecture efficiency across diverse heterogeneous systems. By analyzing the energy consumption of various GNN operations, GCoDE introduces an energy prediction method that improves energy assessment accuracy and identifies energy-efficient solutions. Using a constraint-based random search strategy, GCoDE identifies the optimal solution in 1.5 hours, balancing accuracy and efficiency. Moreover, the integrated co-inference engine in GCoDE enables efficient deployment and execution of GNN co-inference. Experimental results show that GCoDE can achieve up to 44.9x speedup and 98.2% energy reduction compared to existing approaches across diverse applications and system configurations.