Machine learning interpretability through contribution-value plots
| Autor: | Jarke J. van Wijk, Dennis Collaris |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Visual analytics
business.industry Computer science Model prediction 020207 software engineering 02 engineering and technology Machine learning computer.software_genre 01 natural sciences Field (computer science) Visualization 010104 statistics & probability Feature (computer vision) 0202 electrical engineering electronic engineering information engineering Key (cryptography) Artificial intelligence 0101 mathematics business Value (mathematics) computer Interpretability |
| Zdroj: | VINCI |
| DOI: | 10.1145/3430036.3430067 |
| Popis: | The field of explainable artificial intelligence aims to help experts understand complex machine learning models. One key approach is to show the impact of a feature on the model prediction. This helps experts to verify and validate the predictions the model provides. However, many challenges remain open. For example, due to the subjective nature of interpretability, a strict definition of concepts such as the contribution of a feature remains elusive. Different techniques have varying underlying assumptions, which can cause inconsistent and conflicting views. In this work, we introduce Local and Global Contribution-Value plots as a novel approach to visualize feature impact on predictions and the relationship with feature value. We discuss design decisions, and show an exemplary visual analytics implementation that provides new insights into the model. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|