Summary of Graph Neural Networks Automated Design and Deployment on Device-edge Co-inference Systems, by Ao Zhou et al.
Graph Neural Networks Automated Design and Deployment on Device-Edge Co-Inference Systems
by Ao Zhou, Jianlei Yang, Tong Qiao, Yingjie Qi, Zhi Yang, Weisheng Zhao, Chunming Hu
First submitted to arxiv on: 8 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents a framework called GCoDE for optimizing Graph Neural Networks (GNNs) on device-edge co-inference systems. GCoDE co-designs the architecture search and operation mapping across devices and edges, abstracting communication processes to enhance efficiency. This unified optimization approach enables effective evaluation of architecture efficiency in diverse heterogeneous systems. Experimental results show that GCoDE achieves up to 44.9x speedup and 98.2% energy reduction compared to existing approaches. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary GNNs are special kinds of artificial intelligence that work with graphs, like social networks or molecules. Right now, it’s hard to use these GNNs on different devices, like your phone or a supercomputer, because they can be very slow and use too much energy. The researchers created a new system called GCoDE that helps make GNNs work better on different devices by dividing the job into smaller parts and finding the best way to do each part. They tested GCoDE and found it made the GNNs run up to 44.9 times faster and use 98.2% less energy. |
Keywords
* Artificial intelligence * Inference * Optimization
