Summary of Improving Hyperbolic Representations Via Gromov-wasserstein Regularization, by Yifei Yang et al.
Improving Hyperbolic Representations via Gromov-Wasserstein Regularization
by Yifei Yang, Wonjun Lee, Dongmian Zou, Gilad Lerman
First submitted to arxiv on: 15 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computer Vision and Pattern Recognition (cs.CV)
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 research paper proposes a novel regularization mechanism for hyperbolic neural networks to better preserve the geometric structures of original feature spaces. The authors apply the Gromov-Wasserstein (GW) distance as a regularization term within the networks, which quantifies how well the data structure is maintained after embedding. Specifically, they treat the layers as a transport map and calculate the GW distance accordingly. The approach demonstrates consistent enhancements over current state-of-the-art methods across various tasks, including few-shot image classification, semi-supervised graph link prediction, and node classification. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Hyperbolic neural networks are great at modeling complex data structures, but they often lose the original structure when learning representations from data. This paper tries to fix that by using a new way to keep track of how well the original structure is preserved. They use something called the Gromov-Wasserstein distance to make sure the network doesn’t distort the data too much. This helps the network do better on tasks like image classification and graph problems. |
Keywords
» Artificial intelligence » Classification » Embedding » Few shot » Image classification » Regularization » Semi supervised
