Summary of Cotet: Cross-view Optimal Transport For Knowledge Graph Entity Typing, by Zhiwei Hu et al.
COTET: Cross-view Optimal Transport for Knowledge Graph Entity Typing
by Zhiwei Hu, Víctor Gutiérrez-Basulto, Zhiliang Xiang, Ru Li, Jeff Z. Pan
First submitted to arxiv on: 22 May 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computation and Language (cs.CL); Machine Learning (cs.LG)
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 paper introduces Cross-view Optimal Transport for knowledge graph Entity Typing (COTET), a method that leverages both high-level coarse-grained cluster knowledge and fine-grained type knowledge to infer missing entity type instances in knowledge graphs. COTET consists of three modules: Multi-view Generation and Encoder, which captures structured knowledge from different perspectives; Cross-view Optimal Transport, which transports view-specific embeddings to a unified space by minimizing the Wasserstein distance; and Pooling-based Entity Typing Prediction, which aggregates prediction scores from diverse neighbors using a mixture pooling mechanism. The paper also proposes a distribution-based loss function to mitigate false negatives during training. Experimental results show that COTET outperforms existing baselines. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making computers better at understanding what kinds of things are in large networks of information called knowledge graphs. Right now, computers can get confused when they don’t have enough information about what something is. The new method, called COTET, helps by looking at different types of information that can help figure out what something is. It uses a special way to combine this information and then makes predictions about what things are. The results show that COTET works better than other methods. |
Keywords
» Artificial intelligence » Encoder » Knowledge graph » Loss function
