Summary of Core: Data Augmentation For Link Prediction Via Information Bottleneck, by Kaiwen Dong et al.
CORE: Data Augmentation for Link Prediction via Information Bottleneck
by Kaiwen Dong, Zhichun Guo, Nitesh V. Chawla
First submitted to arxiv on: 17 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: 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 The proposed novel data augmentation method, COmplete and REduce (CORE), aims to enhance the performance and robustness of link prediction (LP) models in graph representation learning. By drawing inspiration from the Information Bottleneck principle, CORE learns compact and predictive augmentations for LP models by recovering missing edges while removing noise from graph structures. This approach has been demonstrated to be effective on multiple benchmark datasets, outperforming state-of-the-art methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Link prediction is a key task in graph representation learning with many applications. However, current LP models are often limited by noisy or spurious information in graphs and incomplete data. A new method, CORE, helps solve this problem by recovering missing edges and removing noise from graph structures. This makes LP models more robust and accurate. Tests on several datasets show that CORE is better than other methods at predicting links. |
Keywords
» Artificial intelligence » Data augmentation » Representation learning
