Quanda: An Interpretability Toolkit for Training Data Attribution Evaluation and Beyond

Understand

In recent years, training data attribution (TDA) methods have emerged as a promising direction for the interpretability of neural networks.

• While research around TDA is thriving, limited effort has been dedicated to the evaluation of attributions.
• Similar to the development of evaluation metrics for traditional feature attribution approaches, several standalone metrics have been proposed to evaluate the quality of TDA methods across various contexts.
• However, the lack of a unified framework that allows for systematic comparison limits trust in TDA methods and stunts their widespread adoption.