Summary of Less Is More: One-shot Subgraph Reasoning on Large-scale Knowledge Graphs, by Zhanke Zhou et al.
Less is More: One-shot Subgraph Reasoning on Large-scale Knowledge Graphs
by Zhanke Zhou, Yongqi Zhang, Jiangchao Yao, Quanming Yao, Bo Han
First submitted to arxiv on: 15 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); 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 one-shot-subgraph link prediction method efficiently and adaptively predicts new facts on a knowledge graph. It decouples the prediction procedure into two steps: extracting a subgraph relevant to the query, and predicting on that single subgraph. This approach leverages Personalized PageRank (PPR) heuristics for efficient identification of potential answers and supporting evidence. The method also introduces automated searching for optimal configurations in data and model spaces. Experimental results demonstrate promoted efficiency and leading performances on five large-scale benchmarks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine a powerful tool that can help us find new information on the internet. This tool is called a knowledge graph, and it’s like a huge library where we can store lots of information. But finding specific answers in this massive library can be difficult. The proposed method makes it easier by focusing on a small part of the library that’s related to our question. It uses a special algorithm to find the most relevant information and then uses that information to make predictions about what we might be looking for. This approach is faster and more accurate than previous methods, which is important because knowledge graphs are getting bigger all the time. |
Keywords
* Artificial intelligence * Knowledge graph * One shot
