Relational Local Explanations
Borisov, Vadim, Kasneci, Gjergji
–arXiv.org Artificial Intelligence
The majority of existing post-hoc explanation approaches for machine learning models produce independent, per-variable feature attribution scores, ignoring a critical inherent characteristics of homogeneously structured data, such as visual or text data: there exist latent inter-variable relationships between features. In response, we develop a novel model-agnostic and permutation-based feature attribution approach based on the relational analysis between input variables. As a result, we are able to gain a broader insight into the predictions and decisions of machine learning models. Experimental evaluations of our framework in comparison with state-of-the-art attribution techniques on various setups involving both image and text data modalities demonstrate the effectiveness and validity of our method.
arXiv.org Artificial Intelligence
Feb-11-2023
- Country:
- North America > United States
- California (0.04)
- New Mexico > Los Alamos County
- Los Alamos (0.04)
- Europe
- Switzerland > Basel-City
- Basel (0.04)
- Germany > Baden-Württemberg
- Tübingen Region > Tübingen (0.14)
- Switzerland > Basel-City
- Asia > Middle East
- Jordan (0.04)
- North America > United States
- Genre:
- Research Report
- Promising Solution (0.48)
- New Finding (0.46)
- Research Report
- Industry:
- Law (1.00)
- Information Technology > Security & Privacy (1.00)
- Government (1.00)
- Technology: