Summary of Diverse Explanations From Data-driven and Domain-driven Perspectives in the Physical Sciences, by Sichao Li and Xin Wang and Amanda Barnard
Diverse Explanations From Data-Driven and Domain-Driven Perspectives in the Physical Sciences
by Sichao Li, Xin Wang, Amanda Barnard
First submitted to arxiv on: 1 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- 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 methods have been remarkably successful in material science, providing novel scientific insights, guiding future laboratory experiments, and accelerating materials discovery. Despite the promising performance of these models, understanding the decisions they make is also essential to ensure the scientific value of their outcomes. This paper explores the sources and implications of diverse explanations in ML applications for physical sciences. It examines how different models, explanation methods, levels of feature attribution, and stakeholder needs can result in varying interpretations of ML outputs through three case studies in materials science and molecular property prediction. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about using machine learning to help scientists discover new materials. Machine learning helps by providing insights and guiding future experiments. But it’s also important for scientists to understand how the machine learning models make their decisions. The authors look at three examples where different machine learning models can give different answers. They show that this can happen because of different model types, explanation methods, or levels of detail. The authors want people to know about these differences and how they affect scientific discoveries. |
Keywords
* Artificial intelligence * Machine learning
