Summary of A Survey Of Data-efficient Graph Learning, by Wei Ju et al.
A Survey of Data-Efficient Graph Learning
by Wei Ju, Siyu Yi, Yifan Wang, Qingqing Long, Junyu Luo, Zhiping Xiao, Ming Zhang
First submitted to arxiv on: 1 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Social and Information Networks (cs.SI)
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 tackles a crucial problem in graph neural networks (GNNs), which excel in modeling graph-structured data but struggle when faced with limited annotation resources. Traditional GNNs rely on significant labeled data for training, making them impractical in real-world scenarios where labeling is costly or impossible. To address this challenge, researchers have explored various methods to enhance GNN performance under low-resource settings, such as self-supervised, semi-supervised, and few-shot learning. This paper introduces Data-Efficient Graph Learning (DEGL) as a novel research frontier and presents the first comprehensive survey on DEGL. The authors review recent advances in DEGL from different angles, including the challenges of training GNNs with large labeled data, and highlight promising directions for future research. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making computer models work better when they don’t have a lot of information to learn from. Graph neural networks are great at understanding complex relationships in data, but they need lots of examples to get good at it. The problem is that in the real world, we often don’t have enough labeled data to train these models. To fix this, researchers are exploring new ways to make GNNs work with limited information. This paper introduces a new approach called Data-Efficient Graph Learning and reviews what’s been happening in this area so far. |
Keywords
* Artificial intelligence * Few shot * Gnn * Self supervised * Semi supervised
