Summary of Comprehensible Artificial Intelligence on Knowledge Graphs: a Survey, by Simon Schramm and Christoph Wehner and Ute Schmid
Comprehensible Artificial Intelligence on Knowledge Graphs: A survey
by Simon Schramm, Christoph Wehner, Ute Schmid
First submitted to arxiv on: 4 Apr 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- 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 Machine learning educators can now summarize this abstract as follows: This paper provides a comprehensive overview of comprehensible artificial intelligence (AI) on knowledge graphs, including its history and applications. The authors argue that the concept of explainable AI is overloaded and overlapping with interpretable machine learning, and instead propose the parent concept of comprehensible AI to provide a clear distinction between the two. The survey also introduces a novel taxonomy for comprehensible AI on knowledge graphs, which includes both interpretable machine learning and explainable AI. Furthermore, the authors identify research gaps in the field that can be explored further. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about how artificial intelligence (AI) is used in our daily lives, like on the internet or with self-driving cars. It’s also about how AI can make sense of big data, which is important for things like search engines and social media. The authors are talking about two types of AI: explainable AI and interpretable machine learning. They think that these terms get mixed up sometimes, so they’re introducing a new idea called comprehensible AI to help clear things up. The paper also talks about how we can use AI in the future and what we need to do to make it better. |
Keywords
» Artificial intelligence » Machine learning
