# Graph Neural Networks Automated Design and Deployment on Device-Edge Co-Inference Systems

arXiv: https://arxiv.org/abs/2404.05605 · HTML: https://mlsanity.com/paper/2404.05605/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 22 references that are in the map.
- First posted on arXiv 8 Apr 2024.

## Builds on (most cited first, 15 of 15)

- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [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)
- [Evaluating the Search Phase of Neural Architecture Search](https://mlsanity.com/paper/1902.08142/) (2019)
- [Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks](https://mlsanity.com/paper/2004.13826/) (2020)
- [A Comprehensive Survey on Hardware-Aware Neural Architecture Search](https://mlsanity.com/paper/2101.09336/) (2021)
- [Scene-Graph Augmented Data-Driven Risk Assessment of Autonomous Vehicle Decisions](https://mlsanity.com/paper/2009.06435/) (2020)
- [Branchy-GNN: a Device-Edge Co-Inference Framework for Efficient Point Cloud Processing](https://mlsanity.com/paper/2011.02422/) (2020)
- [Towards Efficient Graph Convolutional Networks for Point Cloud Handling](https://mlsanity.com/paper/2104.05706/) (2021)
- [G-CoS: GNN-Accelerator Co-Search Towards Both Better Accuracy and Efficiency](https://mlsanity.com/paper/2109.08983/) (2021)
- [Hardware-Aware Graph Neural Network Automated Design for Edge Computing Platforms](https://mlsanity.com/paper/2303.10875/) (2023)
- [MaGNAS: A Mapping-Aware Graph Neural Architecture Search Framework for Heterogeneous MPSoC Deployment](https://mlsanity.com/paper/2307.08065/) (2023)
- [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)
- [Architectural Implications of GNN Aggregation Programming Abstractions](https://mlsanity.com/paper/2310.12184/) (2023)

## Built on by (most cited first, 5 of 5)

- [GraNNite: Enabling High-Performance Execution of Graph Neural Networks on Resource-Constrained Neural Processing Units](https://mlsanity.com/paper/2502.06921/) (2025)
- [Onboard Optimization and Learning: A Survey](https://mlsanity.com/paper/2505.08793/) (2025)
- [EcoVLA: Energy-Efficient Device-Edge Co-Inference for Vision-Language-Action Models under Real-Time Constraints](https://mlsanity.com/paper/2608.15502/) (2026)
- [HGNAS: Hardware-Aware Graph Neural Architecture Search for Edge Devices](https://mlsanity.com/paper/2408.12840/) (2024)
- [JaGNet: Detection, Identification and Position Error Correction of GNSS Jamming with Deep Temporal Graphs](https://mlsanity.com/paper/2509.14000/) (2025)

## Abstract (arXiv)

The key to device-edge co-inference paradigm is to partition models into computation-friendly and computation-intensive parts across the device and the edge, respectively. However, for Graph Neural Networks (GNNs), we find that simply partitioning without altering their structures can hardly achieve the full potential of the co-inference paradigm due to various computational-communication overheads of GNN operations over heterogeneous devices. We present GCoDE, the first automatic framework for GNN that innovatively Co-designs the architecture search and the mapping of each operation on Device-Edge hierarchies. GCoDE abstracts the device communication process into an explicit operation and fuses the search of architecture and the operations mapping in a unified space for joint-optimization. Also, the performance-awareness approach, utilized in the constraint-based search process of GCoDE, enables effective evaluation of architecture efficiency in diverse heterogeneous systems. We implement the co-inference engine and runtime dispatcher in GCoDE to enhance the deployment efficiency. Experimental results show that GCoDE can achieve up to 44.9× speedup and 98.2% energy reduction compared to existing approaches across various applications and system configurations.