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

协作研究：III：媒介：针对捷径学习的有效检测和缓解：数据建模框架

• 批准号: 2310260
• 负责人: Xia Hu
• 金额: $ 60万
• 依托单位: William Marsh Rice University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-10-01 至 2027-09-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2310260&HistoricalAwards=false
• 关键词: Collaborative; Research; III; Medium; Towards

Deep Neural Network (DNN) generalization is a challenging problem. Many DNNs do not remain predictive when the distribution of data changes or there are small disturbances to their input. A common reason for this behavior is “shortcut learning”, in which the DNN learns to make decisions based on relationships observed in the data, but that are not causal. These decisions fail when the model is transferred to real-world scenarios because the network has latched onto spurious correlations. This project investigates how to identify and mitigate shortcut learning in DNNs. A successful outcome of this research will lead to advances in theoretical understanding, as well as robust and generalizable DNN algorithms that avoid shortcuts. The education program integrates machine learning, industrial engineering, and health informatics to train students with essential data analytics tools in information systems, as well as 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 generalization in deep learning. The developed data-centric mechanisms could be directly adopted in real-world data analytics systems to mitigate the drawbacks of shortcut learning. The 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. The project also demonstrates how the proposed research innovations could be embedded into two real DNN-based medical informatics systems. The proposed framework uncovers intrinsic properties of shortcut learning by calibrating shortcut features across different types of distribution shifts, and should support both 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.

深度神经网络 (DNN) 泛化是一个具有挑战性的问题，当数据分布发生变化或输入存在微小干扰时，许多 DNN 无法保持预测性，这种行为的常见原因是“捷径学习”，即 DNN 进行学习。根据数据中观察到的关系做出决策，但当模型转移到现实场景时，这些决策会失败，因为网络已经锁定了虚假相关性。这项研究的成功成果将带来理论理解的进步，以及避免走捷径的强大且可推广的 DNN 算法。该教育计划整合了机器学习、工业工程和健康信息学，以培训学生使用基本的数据分析工具。该项目的主要目标是从以数据为中心的角度系统地研究捷径特征的识别和缓解，以促进深度学习中所开发数据的泛化。以中心机制可以直接在现实世界的数据分析系统中采用，以减轻捷径学习的缺点。该项目研究不同级别（包括实例、特征和任务级别）的捷径识别和检测，然后通过数据增强和训练正则化来执行捷径缓解。该项目还展示了如何将所提出的研究创新嵌入到两个真实的基于 DNN 的医学信息学系统中，所提出的框架通过校准不同类型的分布变化的快捷特征来揭示快捷学习的内在属性，并且应该为研究人员和从业者提供支持。这授予 NSF 的法定使命，并通过评估反映使用基金会的智力优点和更广泛的影响审查标准，被认为值得支持。