Error Analysis of Shapley Value-Based Model Explanations: An Informative Perspective

arXiv:2404.13522v1 Announce Type: cross
Abstract: Shapley value attribution is an increasingly popular explainable AI (XAI) method, which quantifies the contribution of each feature to the model's output. However, recent work has shown that most existing methods to implement Shapley value attributions have some drawbacks. Due to these drawbacks, the resulting Shapley value attributions may provide biased or unreliable explanations, which fail to correctly capture the true intrinsic relationships between features and model outputs. Moreover, it is difficult to evaluate these …

abstract analysis arxiv attribution cs.ai cs.lg error explainable ai feature however perspective popular stat.ml type value work xai