重要意思決定のための堅牢なモデル中心型説明手法
Provably Robust Model-Centric Explanations for Critical Decision-Making
訓練済みモデルの挙動をSAT形式でモデル中心に説明する手法を提案し、LIMEやSHAPなどデータ中心の説明手法と比較して、重要用途ではより堅牢で実用的な知見が得られることを示した。
著者: Cecilia G. Morales, Nicholas Gisolfi, Robert Edman, James K. Miller, Artur Dubrawski
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
We recommend using a model-centric, Boolean Satisfiability (SAT) formalism to obtain useful explanations of trained model behavior, different and complementary to what can be gleaned from LIME and SHAP, popular data-centric explanation tools in Artificial Intelligence (AI). We compare and contrast these methods, and show that data-centric methods may yield brittle explanations of limited practical utility. The model-centric framework, however, can offer actionable insights into risks of using AI models in practice. For critical applications of AI, split-second decision making is best informed by robust explanations that are invariant to properties of data, the capability offered by model-centric frameworks.
