Summary of Large Language Model-based Augmentation For Imbalanced Node Classification on Text-attributed Graphs, by Leyao Wang et al.
Large Language Model-based Augmentation for Imbalanced Node Classification on Text-Attributed Graphs
by Leyao Wang, Yu Wang, Bo Ni, Yuying Zhao, Tyler Derr
First submitted to arxiv on: 22 Oct 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Machine Learning (cs.LG); 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 common issue in node classification on graphs: class imbalance. When one class has significantly more instances than others, predictions can become biased, leading to inaccurate results. The authors focus on Text-Attributed Graphs (TAGs), which combine graph structure with rich textual information. To address this problem, they propose Large Language Model-based Augmentation on Text-Attributed Graphs (LA-TAG). This framework leverages large language models to synthesize new node attributes and a textual link predictor to preserve the graph’s structural and contextual information. The authors demonstrate that LA-TAG outperforms existing methods on various datasets and evaluation metrics, highlighting its effectiveness in handling class imbalance. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Node classification on graphs can be biased when one class has more instances than others. This paper proposes a new way to address this issue using Text-Attributed Graphs (TAGs). They combine graph structure with rich textual information. To fix the problem, they use large language models to make up new node attributes and then connect these new nodes to the original graph. This helps keep the graph’s structure and context. The results show that this approach works better than others on different datasets. |
Keywords
» Artificial intelligence » Classification » Large language model
