Summary of Towards Better Benchmark Datasets For Inductive Knowledge Graph Completion, by Harry Shomer et al.
Towards Better Benchmark Datasets for Inductive Knowledge Graph Completion
by Harry Shomer, Jay Revolinsky, Jiliang Tang
First submitted to arxiv on: 14 Jun 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: 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 explores Knowledge Graph Completion (KGC) in an inductive setting, where some entities and relations are unseen during training. Recent benchmarks have been proposed for inductive KGC, but they inadvertently create a shortcut that can be exploited by ignoring relational information. Specifically, the Personalized PageRank (PPR) score achieves strong performance on most datasets. The authors study this issue, propose an alternative dataset construction strategy to mitigate the PPR shortcut, and benchmark popular methods using the new datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about fixing a problem in AI that helps computers learn from incomplete information. Right now, there’s a way to cheat by ignoring some details, which makes it seem like the computer is better at learning than it really is. The authors of this paper found out why this is happening and came up with a new way to test how well different methods work. This will help us understand what AI can really do. |
Keywords
* Artificial intelligence * Knowledge graph
