Year: 2022
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Borisov, Vadim, Kasneci, Gjergji
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4312206357