Summary of Acceleration Algorithms in Gnns: a Survey, by Lu Ma et al.
Acceleration Algorithms in GNNs: A Survey
by Lu Ma, Zeang Sheng, Xunkai Li, Xinyi Gao, Zhezheng Hao, Ling Yang, Wentao Zhang, Bin Cui
First submitted to arxiv on: 7 May 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 proposed paper presents a systematic review of acceleration algorithms in Graph Neural Networks (GNNs), which have shown effectiveness in various graph-based tasks but struggle with inefficiency during training and inference. The authors categorize the existing approaches into three main topics: training acceleration, inference acceleration, and execution acceleration. They provide detailed characterizations of the approaches within each category and discuss their Scalable Graph Learning (SGL) library. Finally, they propose promising directions for future research. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary GNNs are super powerful tools that help us understand and work with complicated graph structures. But right now, it takes a lot of computer power to use them effectively. To solve this problem, scientists have come up with many different ways to speed up GNNs. In this paper, the authors take all these ideas and organize them into three main groups: making training faster, making inference faster, and making the whole process run smoother. They also talk about a special library they created that makes it easier for people to use these accelerated GNNs. |
Keywords
» Artificial intelligence » Inference
