Summary of Graph Data Augmentation with Gromow-wasserstein Barycenters, by Andrea Ponti
Graph data augmentation with Gromow-Wasserstein Barycenters
by Andrea Ponti
First submitted to arxiv on: 12 Apr 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 novel augmentation strategy for graphs operates in a non-Euclidean space, leveraging graphon estimation to model generative mechanisms of network sequences. The approach improves performance of graph classification models, as demonstrated by computational results. The method also provides a means to validate different graphon estimation approaches and approximates the true graphon using the Gromow-Wasserstein distance. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper proposes an innovative way to make large and diverse graph datasets for training, which is important because deep learning methods have been successful in classifying graphs. The method works by modeling how network sequences are generated, and it does this by operating in a non-Euclidean space where graphs live. This approach is new because other data augmentation techniques don’t work well with graphs, which are complex and different from images or numbers. |
Keywords
* Artificial intelligence * Classification * Data augmentation * Deep learning
