Evaluating Groups of Features via Consistency, Contiguity, and Stability

Chaehyeon Kim, Weiqiu You, Shreya Havaldar, Eric Wong

Keywords: Feature Attribution, Explainability, Group Evaluation, Group Attribution

TL;DR: We study consistency, contiguity, and stability for groups of features and find that modern grouping methods are no better than patches.

Abstract: Feature attributions explain model predictions by assigning importance scores to input features. In high-dimensional data such as images, these scores are often assigned to groups of features at a time. There are a variety of strategies for creating these groups, ranging from simple patches to deep-learning-based segmentation algorithms. What makes certain groups better than others for explanations? We formally define three key criteria for interpretable groups of features: consistency, contiguity, and stability. Surprisingly, we find that patch-based groups outperform groups created via modern segmentation tools.

Submission Number: 147