Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2404.05605 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909163372675072 |
|---|---|
| author | Zhou, Ao Yang, Jianlei Qiao, Tong Qi, Yingjie Yang, Zhi Zhao, Weisheng Hu, Chunming |
| author_facet | Zhou, Ao Yang, Jianlei Qiao, Tong Qi, Yingjie Yang, Zhi Zhao, Weisheng Hu, Chunming |
| contents | 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 $44.9\times$ speedup and $98.2\%$ energy reduction compared to existing approaches across various applications and system configurations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_05605 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Graph Neural Networks Automated Design and Deployment on Device-Edge Co-Inference Systems Zhou, Ao Yang, Jianlei Qiao, Tong Qi, Yingjie Yang, Zhi Zhao, Weisheng Hu, Chunming Machine Learning Artificial Intelligence 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 $44.9\times$ speedup and $98.2\%$ energy reduction compared to existing approaches across various applications and system configurations. |
| title | Graph Neural Networks Automated Design and Deployment on Device-Edge Co-Inference Systems |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2404.05605 |