Summary of Argumentative Causal Discovery, by Fabrizio Russo et al.
Argumentative Causal Discovery
by Fabrizio Russo, Anna Rapberger, Francesca Toni
First submitted to arxiv on: 18 May 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 Causal discovery is a crucial step in building scientific knowledge without relying on expensive or impossible randomized control trials. This paper explores how symbolic representations can support causal discovery by deploying assumption-based argumentation (ABA) and causality theories to learn graphs that reflect causal dependencies in the data. The method exhibits desirable properties, including the ability to retrieve ground-truth causal graphs under natural conditions. Experimental results show that our approach compares well against established baselines on four datasets from standard benchmarks in causal discovery. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Causal discovery is like trying to figure out what causes things to happen in the world. It’s a way to build scientific knowledge without doing super expensive or impossible experiments. This paper shows how using special kinds of symbols and rules can help us do that. They use something called assumption-based argumentation (ABA) and combine it with ideas about causality to create graphs that show what causes things to happen in the data. The results are really good and compare well to other ways people have tried to do this. |
