.png){kind=icon}
返回
Impossibility theorems for feature attribution
.png){kind=icon}
OA
AI
DOI：10.1073/pnas.2304406120.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Despite a sea of interpretability methods that can produce plausible explanations, the field has also empirically seen many failure cases of such methods. In light of these results, it remains unclear for practitioners how to use these methods and choose between them in a principled way. In this paper, we show that for moderately rich model classes (easily satisfied by neural networks), any feature attribution method that is complete and linear-for example, Integrated Gradients and Shapley Additive Explanations (SHAP)-can provably fail to improve on random guessing for inferring model behavior. Our results apply to common end-tasks such as characterizing local model behavior, identifying spurious features, and algorithmic recourse. One takeaway from our work is the importance of concretely defining end-tasks: Once such an end-task is defined, a simple and direct approach of repeated model evaluations can outperform many other complex feature attribution methods.
Keyword:
interpretability
feature attribution
explainable AI
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
P
IF:
9.1
论文数:
10.8W
被引数:
73.5W
机构
引用论文
.png){kind=icon}
Stability of Iodine in Iodized Salt Used for Correction of Iodine-Deficiency Disorders. II用于纠正碘缺乏病的碘盐中碘的稳定性。二
PREAI
分享收藏
分享收藏Cell-free Protein Synthesis in an Autoinduction System for NMR Studies of Protein–Protein Interactions用于NMR研究蛋白质-蛋白质相互作用的自动诱导系统中的无细胞蛋白质合成
PREAI
分享收藏
查看更多内容