In the rapidly growing literature on explanation algorithms, it often remains unclear what precisely these algorithms are for and how they should be used. In this position paper, we argue for a novel and pragmatic perspective: Explainable machine learning needs to recognize its parallels with applied statistics. Concretely, explanations are statistics of high-dimensional functions, and we should think about them analogously to traditional statistical quantities. Among others, this implies that we must think carefully about the matter of interpretation, or how the explanations relate to intuitive questions that humans have about the world. The fact that this is scarcely being discussed in research papers is one of the main drawbacks of the current literature. Moving forward, the analogy between explainable machine learning and applied statistics suggests fruitful ways for how research practices can be improved.
Statistical Inference for Explainable Boosting Machines
School of Economics, Fudan University（复旦大学经济学院）；Department of Statistics and Data Science, The Wharton School, University of Pennsylvania（宾夕法尼亚大学沃顿商学院统计与数据科学系）
Explainable AI Isn't Enough! Rethinking Algorithmic Contestability
LMU Munich（慕尼黑莱茵河大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；Munich Center for Mathematical Philosophy (MCMP)（慕尼黑数学哲学中心）；CZS Institute for Artificial Intelligence and Law（CZS人工智能与法律研究所）
Which products activate a product? An explainable machine learning approach
IMT School for Advanced Studies（IMT高等研究学院）；Centro Ricerche Enrico Fermi（恩里科·费米研究中心）；Joint Research Centre（联合研究中心）；Institute for Complex Systems, CNR（国家研究委员会复杂系统研究所）；Sapienza University of Rome（罗马智慧大学）
A Machine Learning Pipeline for Multiple Sclerosis Biomarker Discovery: Comparing explainable AI and Traditional Statistical Approaches
Department of Computer Science , University of Pisa（计算机科学系，比萨大学）；Department of Clinical and Biological Sciences, University of Torino（临床与生物科学系，都灵大学）；Department of Computer Sciences, University of Torino（计算机科学系，都灵大学）；Department of Computer Science and Engineering, University of Bologna（计算机科学与工程系，博洛尼亚大学）
该研究构建整合八个 PBMC 微阵列数据集的机器学习流水线，用 XGBoost 与 SHAP 发现 MS 生物标志物，并与 DEA 比较，证明二者互补且可揭示相关疾病通路。
Higher-Order Feature Attribution: Bridging Statistics, Explainable AI, and Topological Signal Processing
School of Engineering, The University of Edinburgh（爱丁堡大学工程学院）；Causality in Healthcare AI Hub (CHAI)（医疗AI因果性研究中心）；Department of Electrical and Computer Engineering, Stony Brook University（石溪大学电气与计算机工程系）
