Summary of Yoso: You-only-sample-once Via Compressed Sensing For Graph Neural Network Training, by Yi Li et al.
YOSO: You-Only-Sample-Once via Compressed Sensing for Graph Neural Network Training
by Yi Li, Zhichun Guo, Guanpeng Li, Bingzhe Li
First submitted to arxiv on: 8 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 This paper proposes a novel algorithm called YOSO (You-Only-Sample-Once) for efficient training of graph neural networks (GNNs). The authors focus on reducing latency and computational complexity during the training stage, while maintaining prediction accuracy. To achieve this, they introduce a compressed sensing (CS)-based sampling and reconstruction framework that samples nodes only once at the input layer and reconstructs them losslessly at the output layer per epoch. This approach avoids costly computations in traditional CS methods and ensures high-probability accuracy retention equivalent to full node participation. Experimental results on node classification and link prediction demonstrate the effectiveness and efficiency of YOSO, reducing GNN training by an average of 75% compared to state-of-the-art methods while maintaining accuracy on par with top-performing baselines. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary YOSO is a new way to train graph neural networks that makes them faster and more efficient. Imagine you’re trying to analyze a huge network of connections, like the internet or a social media platform. Training GNNs can be slow and take up a lot of computer power. YOSO helps solve this problem by only looking at certain parts of the network at a time, which makes training much faster. It still gets the same accurate results as other methods, but uses less energy and is more efficient. |
Keywords
» Artificial intelligence » Classification » Gnn » Probability
