Constructive Interpretability with CoLabel: Corroborative Integration, Complementary Features, and Collaborative Learning
Constructive Interpretability with CoLabel: Corroborative Integration, Complementary Features, and Collaborative Learning
复制标题
DOI：
10.1109/cogmi56440.2022.00021
复制
发表时间：
2022-05
期刊：
影响因子：
--
通讯作者：
Abhijit Suprem;Sanjyot Vaidya;Suma Cherkadi;Purva Singh;J. E. Ferreira;C. Pu
中科院分区：
文献类型：
--
作者：
Abhijit Suprem;Sanjyot Vaidya;Suma Cherkadi;Purva Singh;J. E. Ferreira;C. Pu
具有可解释预测的机器学习模型越来越受欢迎，特别是对于需要偏差检测和风险缓解的现实世界，任务关键型应用程序。固有的可解释性，即模型从一开始就为可解释性而设计，为模型预测和性能提供直观的见解和透明的解释。在本文中，我们提出了CoLabel，一种建立可解释模型的方法，其解释植根于地面事实。我们展示了CoLabel在车辆特征提取应用程序中的车辆模型识别（VMMR）的背景下。通过构造，CoLabel使用可解释的特征（如车辆颜色，类型和制造）的组合执行VMMR，所有这些都基于地面真实标签的可解释注释。首先，CoLabel执行确证集成来连接多个数据集，每个数据集都有一个所需的颜色，类型和品牌注释的子集。然后，CoLabel使用可分解的分支来提取与所需注释相对应的互补特征。最后，CoLabel将它们融合在一起进行最终预测。在特征融合过程中，CoLabel协调互补分支，使VMMR特征相互兼容，并可以投影到同一语义空间进行分类。凭借固有的可解释性，CoLabel实现了优于最先进的黑盒模型的性能，在CompCars，Cars196和BoxCars116K上的精度分别为0.98，0.95和0.94。CoLabel提供直观的解释，由于建设性的可解释性，并随后在关键任务的情况下实现高准确性和可用性。
Machine learning models with explainable predictions are increasingly sought after, especially for real-world, mission-critical applications that require bias detection and risk mitigation. Inherent interpretability, where a model is designed from the ground-up for interpretability, provides intuitive insights and transparent explanations on model prediction and performance. In this paper, we present CoLabel, an approach to build interpretable models with explanations rooted in the ground truth. We demonstrate CoLabel in a vehicle feature extraction application in the context of vehicle make-model recognition (VMMR). By construction, CoLabel performs VMMR with a composite of interpretable features such as vehicle color, type, and make, all based on interpretable annotations of the ground truth labels. First, CoLabel performs corroborative integration to join multiple datasets that each have a subset of desired annotations of color, type, and make. Then, CoLabel uses decomposable branches to extract complementary features corresponding to desired annotations. Finally, CoLabel fuses them together for final predictions. During feature fusion, CoLabel harmonizes complementary branches so that VMMR features are compatible with each other and can be projected to the same semantic space for classification. With inherent interpretability, CoLabel achieves superior performance to the state-of-the-art black-box models, with accuracy of 0.98, 0.95, and 0.94 on CompCars, Cars196, and BoxCars116K, respectively. CoLabel provides intuitive explanations due to constructive interpretability, and subsequently achieves high accuracy and usability in mission-critical situations.