A Consistent and Efficient Evaluation Strategy for Attribution Methods
This work addresses a critical problem for researchers and practitioners in interpretable machine learning by providing a more efficient and reliable way to evaluate attribution methods, though it is incremental as it builds on prior perturbation-based strategies.
The paper tackles the inconsistency and high computational cost of existing evaluation strategies for feature attribution methods in image analysis by proposing a new framework called ROAD, which reduces computational costs by up to 99% and improves consistency among evaluations.
With a variety of local feature attribution methods being proposed in recent years, follow-up work suggested several evaluation strategies. To assess the attribution quality across different attribution techniques, the most popular among these evaluation strategies in the image domain use pixel perturbations. However, recent advances discovered that different evaluation strategies produce conflicting rankings of attribution methods and can be prohibitively expensive to compute. In this work, we present an information-theoretic analysis of evaluation strategies based on pixel perturbations. Our findings reveal that the results are strongly affected by information leakage through the shape of the removed pixels as opposed to their actual values. Using our theoretical insights, we propose a novel evaluation framework termed Remove and Debias (ROAD) which offers two contributions: First, it mitigates the impact of the confounders, which entails higher consistency among evaluation strategies. Second, ROAD does not require the computationally expensive retraining step and saves up to 99% in computational costs compared to the state-of-the-art. We release our source code at https://github.com/tleemann/road_evaluation.