构建真实分子数据的可解释AI评测基准，揭示现有方法局限
B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data
- 基于真实分子数据构建多任务评测基准，提供已知推理依据
- 发现现有图神经网络可解释方法在分子领域存在显著偏差
- 适合药物研发与可解释性研究者评估模型可信度
在化学信息学和药物发现中，理解深度学习模型预测背后的推理过程至关重要，因为分子结构决定其性质。然而，当前该领域的可解释人工智能（XAI）评估框架常依赖人工数据或简化任务，采用与真实场景脱节的数据驱动指标，无法有效衡量解释的忠实性。为此，我们提出B-XAIC，一个基于真实分子数据、涵盖多样任务并具有已知真值推理依据的新型评测基准。通过在B-XAIC上的全面评估，我们揭示了现有GNN可解释方法在分子领域中的局限性。该基准为深入理解XAI的忠实性提供了宝贵资源，有助于推动更可靠、可解释模型的发展。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。