Guarantee Regions for Local Explanations
CoRR(2024)
摘要
Interpretability methods that utilise local surrogate models (e.g. LIME) are
very good at describing the behaviour of the predictive model at a point of
interest, but they are not guaranteed to extrapolate to the local region
surrounding the point. However, overfitting to the local curvature of the
predictive model and malicious tampering can significantly limit extrapolation.
We propose an anchor-based algorithm for identifying regions in which local
explanations are guaranteed to be correct by explicitly describing those
intervals along which the input features can be trusted. Our method produces an
interpretable feature-aligned box where the prediction of the local surrogate
model is guaranteed to match the predictive model. We demonstrate that our
algorithm can be used to find explanations with larger guarantee regions that
better cover the data manifold compared to existing baselines. We also show how
our method can identify misleading local explanations with significantly poorer
guarantee regions.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要