Summary of Explanation-preserving Augmentation For Semi-supervised Graph Representation Learning, by Zhuomin Chen et al.
Explanation-Preserving Augmentation for Semi-Supervised Graph Representation Learning
by Zhuomin Chen, Jingchao Ni, Hojat Allah Salehi, Xu Zheng, Esteban Schafir, Farhad Shirani, Dongsheng Luo
First submitted to arxiv on: 16 Oct 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 method for graph representation learning called Explanation-Preserving Augmentation (EPA), which leverages graph explanation techniques to generate augmented graphs that preserve the semantics of their original counterparts. EPA first trains a graph explainer using labeled data to infer sub-structures most relevant to a graph’s semantics, and then uses these explanations to generate semantics-preserving augmentations for self-supervised GRL. The proposed approach is demonstrated to outperform state-of-the-art GRL methods on various benchmark datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a new way to learn representations of graphs using ideas from explaining what makes a graph important. It trains a special kind of model that can understand what parts of the graph are most meaningful, and then uses this understanding to create new versions of the graph that still keep its essential features. This approach is shown to be better than other methods for learning graph representations. |
Keywords
» Artificial intelligence » Representation learning » Self supervised » Semantics
