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

TL;DR

Quanda is an open-source Python toolkit that standardizes the evaluation and benchmarking of training data attribution methods, enhancing their interpretability and trustworthiness in neural network analysis.

Contribution

It introduces a unified framework and comprehensive metrics for evaluating TDA methods, facilitating systematic comparison and broader adoption.

Findings

Provides a comprehensive set of evaluation metrics

Enables seamless integration with existing TDA tools

Supports systematic benchmarking of TDA methods

Abstract

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. To address this research gap, we introduce Quanda, a Python toolkit designed to facilitate the evaluation of TDA methods. Beyond offering a comprehensive set of evaluation metrics, Quanda provides a uniform interface for seamless integration with existing TDA implementations across different repositories, thus enabling systematic benchmarking. The toolkit is user-friendly, thoroughly tested, well-documented, and available as an open-source library on PyPi and under https://github.com/dilyabareeva/quanda.