A key challenge for decision makers when incorporating black box machine learned models into practice is being able to understand the predictions provided by these models. One proposed set of methods is training surrogate explainer models which approximate the more complex model. Explainer methods are generally classified as either local or global, depending on what portion of the data space they are purported to explain. The improved coverage of global explainers usually comes at the expense of explainer fidelity. One way of trading off the advantages of both approaches is to aggregate several local explainers into a single explainer model with improved coverage. However, the problem of aggregating these local explainers is computationally challenging, and existing methods only use heuristics to form these aggregations.
In this paper we propose a local explainer aggregation method which selects local explainers using non-convex optimization. In contrast to other heuristic methods, we use an integer optimization framework to combine local explainers into a near-global aggregate explainer. Our framework allows a decision-maker to directly tradeoff coverage and fidelity of the resulting aggregation through the parameters of the optimization problem. We also propose a novel local explainer algorithm based on information filtering. We evaluate our algorithmic framework on two healthcare datasets---the Parkinson's Progression Marker Initiative (PPMI) data set and a geriatric mobility dataset---which is motivated by the anticipated need for explainable precision medicine. Our method outperforms existing local explainer aggregation methods in terms of both fidelity and coverage of classification and improves on fidelity over existing global explainer methods, particularly in multi-class settings where state-of-the-art methods achieve 70% and ours achieves 90%.
Tree-Guided Rare Feature Selection and Logic Aggregation with Electronic Health Records Data
University of Connecticut（康涅狄格大学）；University of Connecticut Health Center (UCHC)（康涅狄格大学健康中心）；Weill Cornell Medical College, Cornell University（康奈尔大学威尔医学院）
A Cognitive Explainer for Fetal ultrasound images classifier Based on Medical Concepts
Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；University Town of Shenzhen, Nanshan District, Shenzhen（深圳大学城南山区深圳校区）；Beijing Tsinghua Changgung Hospital（北京清华大学长庚医院）；Peking University Shenzhen Hospital（北京大学深圳医院）；Shenzhen Baoan District Maternal and Child Health Hospital（深圳宝安区妇幼保健医院）
Sera: Semantic Representation Aggregation with Knowledge and LLM for Reliable and Interpretable Battery Health Forecasting
Singapore Institute of Technology（新加坡理工学院）；Singapore University of Social Sciences（新加坡社科大学）；Shanghai Jiao Tong University（上海交通大学）；Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局）；Institute of Advanced Intelligence and Computing (IAIC), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局高级智能与计算研究所）；Institute of Materials Research and Engineering (IMRE), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局材料研究与工程研究所）
Knowledge & Data Engineering Group, University of Kassel, Germany（卡塞尔大学知识与数据工程组）；Interdisciplinary Research Center for Information System Design, University of Kassel, Germany（卡塞尔大学信息系统设计跨学科研究中心）
GnnXemplar: Exemplars to Explanations -- Natural Language Rules for Global GNN Interpretability
Dept. of CSE, IIT Delhi（印度德里理工学院计算机科学与工程系）；Fujitsu Research of India, Bangalore（印度班加罗尔富士通印度研究机构）；Dept. of CSE and Yardi ScAI, IIT Delhi（印度德里理工学院计算机科学与工程系）
DPsurv: Dual-Prototype Evidential Fusion for Uncertainty-Aware and Interpretable Whole-Slide Image Survival Prediction
National University of Singapore；National University of Singapore Guangzhou Research Translation；Innovation Institute；Imperial College London；Peking Union Medical College Hospital, Chinese Academy of Medical Sciences \& Peking Union Medical College；Hunan University；Institute of High Performance Computing, Agency for Science, Technology；Research (A STAR)
Data-Driven Integration Kernels for Interpretable Nonlocal Operator Learning
Department of Earth System Science（地球系统科学系）；University of California, Irvine（加州大学伊维福分校）；Department of Computing and Data Science（计算与数据科学系）；Boston University（波士顿大学）；The Center for Atmosphere Ocean Science（大气海洋科学中心）；New York University（纽约大学）；NVIDIA Corporation（NVIDIA公司）；Faculty of Geosciences and Environment（地球科学与环境学院）；University of Lausanne（洛桑大学）；Expertise Center for Climate Extremes（极端气候专家中心）
