Xiuyi Fan

Explainable AI for Classification using Probabilistic Logic Inference

2020 · arXiv (Cornell University)

The overarching goal of Explainable AI is to develop systems that not only exhibit intelligent behaviours, but also are able to explain their rationale and reveal insights. In explainable machine learning, methods that produce a …

Evaluating the Correctness of Explainable AI Algorithms for Classification

2021 · arXiv (Cornell University)

Explainable AI has attracted much research attention in recent years with feature attribution algorithms, which compute "feature importance" in predictions, becoming increasingly popular. However, there is little analysis of the validity of these algorithms as …