Model interpretations are often used in practice to extract real world insights from machine learning models. These interpretations have a wide range of applications; they can be presented as business recommendations or used to evaluate model bias. It is vital for a data scientist to choose trustworthy interpretations to drive real world impact. Doing so requires an understanding of how the accuracy of a model impacts the quality of standard interpretation tools. In this paper, we will explore how a model's predictive accuracy affects interpretation quality. We propose two metrics to quantify the quality of an interpretation and design an experiment to test how these metrics vary with model accuracy. We find that for datasets that can be modeled accurately by a variety of methods, simpler methods yield higher quality interpretations. We also identify which interpretation method works the best for lower levels of model accuracy.
WLFM: A Well-Logs Foundation Model for Multi-Task and Cross-Well Geological Interpretation
Institute of Advanced Technology, University of Science and Technology of China（科学技术大学先进技术研究所）；Department of Automation, University of Science and Technology of China（科学技术大学自动化系）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合国家科学中心人工智能研究所）
DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?
Panjab University（旁遮普大学）；OpenMined（OpenMined组织）；Manipal Institute of Technology（马尼帕尔理工学院）；Carnegie Mellon University（卡内基梅隆大学）；IIT Jodhpur（印度理工学院焦特布尔分校）；Ford Motor Company（福特汽车公司）；Innopolis University（因诺波利斯大学）；University of California, San Diego（加利福尼亚大学圣迭戈分校）；University of Oxford（牛津大学）
Deep ROC Analysis and AUC as Balanced Average Accuracy to Improve Model Selection, Understanding and Interpretation
Ottawa Hospital Research Institute（渥太华医院研究所）；Institute of Clinical Evaluative Sciences（临床评估科学研究所）；Department of Family Medicine（家庭医学系）；School of Epidemiology and Public Health（流行病学与公共卫生学院）；University of Ottawa（渥太华大学）；Bruyère Research Institute（布鲁耶尔研究所）；Department of Systems Design Engineering（系统设计工程系）；Vision and Image Processing Lab（视觉与图像处理实验室）；Faculty of Engineering（工程学院）；University of Waterloo（滑铁卢大学）；Fondazione Bruno Kessler Research Institute（布鲁诺·凯斯勒基金会研究所）；Department of Psychology and Cognitive Science（心理学与认知科学系）；University of Trento（特伦托大学）；Department of Cardiology（心脏病学系）；Paracelsus Medical University of Salzburg（萨尔茨堡巴拉塞尔苏斯医科大学）；e-health group（电子健康小组）
Smart Data Representations: Impact on the Accuracy of Deep Neural Networks
Institute for Automation and Applied Informatics, Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院自动化与应用信息学研究所）；Cluster of Excellence Machine Learning, University of Tübingen（蒂宾根大学机器学习卓越集群）
Enhancing Decision Tree based Interpretation of Deep Neural Networks through L1-Orthogonal Regularization
Fraunhofer Institute for Manufacturing Engineering and Automation IPA（弗劳恩霍夫制造工程与自动化研究所IPA）；University of Stuttgart（斯图加特大学）；Stuttgart Media University（斯图加特媒体大学）
