Collaborative Research: III: Medium: Towards Effective Detection and Mitigation for Shortcut Learning: A Data Modeling Framework

深度神经网络(DNN)的泛化已成为一个具有挑战性的问题。当数据分布发生变化或输入中存在小干扰时，许多DNN不能保持预测性。这一挑战的一个主要原因是捷径学习，它指的是基于数据中存在的但不是因果的关系做出决策。当模型由于虚假的相关性被转移到真实世界的场景时，这些决定就失败了。这个项目是研究深度学习中的捷径识别和缓解。这项研究的成功结果将有助于提供理论上的理解，并开发健壮和可推广的DNN算法来分析具有各种类型快捷方式的数据集。该教育项目整合了机器学习、工业工程和健康信息学，旨在培训学生使用信息系统中基本的数据分析工具，以吸引、指导和留住代表不足的群体的成员。该项目的主要目标是从以数据为中心的角度系统地调查快捷特征的识别和缓解，以促进深度学习的推广。开发的以数据为中心的机制可以直接用于真实世界的数据分析系统。具体地说，本项目从实例、特征和任务三个不同的层次研究捷径识别和检测，然后通过数据扩充和训练正则化来执行捷径缓解。该项目还演示了如何将提出的研究创新嵌入到两个基于DNN的真实医学信息学系统中。拟议的框架通过校准来自不同分布偏移类别的快捷特征来揭示快捷学习的内在属性，并使研究人员和实践者能够理解和采用它们。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

Generalization of Deep Neural Networks (DNNs) has become a challenging problem. Many DNNs do not remain predictive when the distribution of data changes or there are small disturbances in the input. A major reason for this challenge is shortcut learning, which refer to decisions based on relationships in the data that exist, but which are not causal. These decisions fail when the model is transferred to real-world scenarios because of spurious correlations. This project is to investigate shortcut identification and mitigation in deep learning. The successful outcome of this research will lead to advances in providing theoretical understandings, and developing robust and generalizable DNN algorithms to analyze datasets with various types of shortcuts. The education program that integrates machine learning, industrial engineering, and health informatics is to train students with essential data analytics tools in information systems, to attract, mentor and retain members from underrepresented groups.The primary goal of this project is to systematically investigate the identification and mitigation of shortcut features from a data-centric perspective to facilitate the generalization of deep learning. The developed data-centric mechanisms could be directly adopted in real-world data analytics systems. Specifically, this project studies shortcut identification and detection at different levels, including instance-, feature-, and task-levels, and then performs shortcut mitigation through data augmentation and training regularization. This project also demonstrates how the proposed research innovations could be embedded in two DNN based real medical informatics systems. The proposed frameworks uncover the intrinsic properties of shortcut learning by calibrating shortcut features from different categories of distribution shift, and enable their comprehension and adoption for researchers and practitioners.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.