B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data
This provides a valuable resource for improving XAI in drug discovery and cheminformatics, though it is incremental as it builds on existing evaluation frameworks.
The authors tackled the problem of evaluating Explainable AI (XAI) methods for Graph Neural Networks in cheminformatics by introducing B-XAIC, a benchmark based on real-world molecular data with ground-truth rationales, which revealed limitations in existing XAI methods.
Understanding the reasoning behind deep learning model predictions is crucial in cheminformatics and drug discovery, where molecular design determines their properties. However, current evaluation frameworks for Explainable AI (XAI) in this domain often rely on artificial datasets or simplified tasks, employing data-derived metrics that fail to capture the complexity of real-world scenarios and lack a direct link to explanation faithfulness. To address this, we introduce B-XAIC, a novel benchmark constructed from real-world molecular data and diverse tasks with known ground-truth rationales for assigned labels. Through a comprehensive evaluation using B-XAIC, we reveal limitations of existing XAI methods for Graph Neural Networks (GNNs) in the molecular domain. This benchmark provides a valuable resource for gaining deeper insights into the faithfulness of XAI, facilitating the development of more reliable and interpretable models.