Summary of Learning Structured Representations by Embedding Class Hierarchy with Fast Optimal Transport, By Siqi Zeng et al.
Learning Structured Representations by Embedding Class Hierarchy with Fast Optimal Transport
by Siqi Zeng, Sixian Du, Makoto Yamada, Han Zhao
First submitted to arxiv on: 4 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 approach to embedding structured knowledge into feature representations during supervised learning. Building on previous work that used the Cophenetic Correlation Coefficient (CPCC) as a regularizer, this method addresses limitations in class means by incorporating the Earth Mover’s Distance (EMD) to measure pairwise distances among classes in the feature space. The proposed exact EMD method generalizes previous work and recovers the existing algorithm when class-conditional distributions are Gaussian. To improve computational efficiency, four EMD approximation variants are introduced, including an Optimal Transport-CPCC family that runs in linear time. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper finds a way to make computers learn better from labels. Labels can have complicated structures, like trees, and the computer needs to understand this structure when learning. The authors take an old idea called Cophenetic Correlation Coefficient (CPCC) and add new features that help it work better. They also come up with ways to make it faster without losing accuracy. This is important because computers need to learn quickly to process lots of data. |
Keywords
» Artificial intelligence » Embedding » Supervised
