When training a predictive model over medical data, the goal is sometimes to gain insights about a certain disease. In such cases, it is common to use feature importance as a tool to highlight significant factors contributing to that disease. As there are many existing methods for computing feature importance scores, understanding their relative merits is not trivial. Further, the diversity of scenarios in which they are used lead to different expectations from the feature importance scores. While it is common to make the distinction between local scores that focus on individual predictions and global scores that look at the contribution of a feature to the model, another important division distinguishes model scenarios, in which the goal is to understand predictions of a given model from natural scenarios, in which the goal is to understand a phenomenon such as a disease. We develop a set of axioms that represent the properties expected from a feature importance function in the natural scenario and prove that there exists only one function that satisfies all of them, the Marginal Contribution Feature Importance (MCI). We analyze this function for its theoretical and empirical properties and compare it to other feature importance scores. While our focus is the natural scenario, we suggest that our axiomatic approach could be carried out in other scenarios too.
Interpreting Deep Learning Models with Marginal Attribution by Conditioning on Quantiles
University of Hamburg(汉堡大学);QED Actuaries & Consultants(QED精算咨询公司);University of the Witwatersrand(威特沃特斯兰德大学);City, University of London(伦敦城市大学);ETH Zurich(苏黎世联邦理工学院)
Leibniz Institute for Prevention Research & Epidemiology – BIPS(莱布尼茨预防研究与流行病学研究所——BIPS);University of Bremen(不来梅大学);King’s College London(伦敦国王学院);University of Copenhagen(哥本哈根大学)
Transfer Learning with Dynamic Distribution Adaptation
Microsoft Research Asia(微软亚洲研究院);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);Nanyang Technological University(南洋理工大学);Qian Xuesen Laboratory of Space Technology, China Academy of Space Technology(中国空间技术研究院钱学森空间技术实验室);Hong Kong University of Science and Technology(香港科技大学)
Conditional Feature Importance with Generative Modeling Using Adversarial Random Forests
Leibniz Institute for Prevention Research & Epidemiology – BIPS(莱布尼茨预防研究与流行病学研究所 – BIPS);Faculty of Mathematics and Computer Science, University of Bremen(不来梅大学数学与计算机科学学院);Berlin School of Economics and Law(柏林经济与法律学院);University of Copenhagen(哥本哈根大学)