FMitF: Collaborative Research: Track I: Embedding Constraint Reasoning in Machine Learning for Better Prediction and Decision-making

FMITF：协作研究：第一轨道：在机器学习中嵌入约束推理以实现更好的预测和决策

• 批准号: 1918327
• 负责人: Yexiang Xue
• 金额: $ 40.68万
• 依托单位: Purdue University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-09-01 至 2024-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1918327&HistoricalAwards=false
• 关键词: FMitF; Collaborative; Research; Track; Embedding

The emergence of large-scale data-driven machine learning and optimization methods has led to successful applications in areas as diverse as finance, marketing, retail, and health care. Yet, many application domains remain out of reach for these methods, when applied in isolation. In the area of medical robotics, for example, it is crucial to develop systems that can recognize, guide, support, or correct surgical procedures. This is particularly important for next-generation trauma care systems that allow life-saving surgery to be performed remotely in the presence of unreliable bandwidth communications. For such systems, machine learning models have been developed that can recognize certain patterns, but they are unable to perform under complex physical or operational constraints. Using constraint-based optimization methods, on the other hand, would allow the generation of feasible surgical plans; but currently, there is no mechanism to represent and evaluate such knowledge under complex environments. To leverage the required capabilities for real-life applications, this project develops an integrated method that Embeds Constraint Reasoning in Machine Learning (ECOR-ML). The researchers intend to demonstrate the effectiveness of ECOR-ML in the context of medical robotics. Prior research indicates that the integration of constraint reasoning and machine learning is essential for the development of safe and efficient technologies in this domain. The project aims to advance both machine learning and constraint reasoning technology, and will promote the cross-fertilization of formal and applied research in the areas of machine learning, constraint learning, and robotics.The approach in this project provides a scalable method for machine learning over structured domains. The core idea is to augment machine learning algorithms with a constraint reasoning module that represents physical and operational requirements. Specifically, this research proposes to embed decision diagrams, a popular constraint reasoning tool, as a fully-differentiable layer in deep neural networks. By enforcing the constraints, the output of generative models can now provide assurances of safety, correctness, and/or fairness. Moreover, ECOR-ML possesses a smaller modeling space than traditional machine learning approaches, allowing machine learning algorithms to learn faster and generalize better.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.

大规模数据驱动的机器学习和优化方法的出现，导致了在金融、营销、零售和医疗保健等领域的成功应用。然而，当孤立地应用这些方法时，许多应用程序领域仍然遥不可及。例如，在医疗机器人领域，开发能够识别、指导、支持或纠正手术过程的系统是至关重要的。这对于下一代创伤护理系统尤其重要，该系统允许在存在不可靠的带宽通信的情况下远程执行挽救生命的手术。对于这样的系统，已经开发了能够识别某些模式的机器学习模型，但它们无法在复杂的物理或操作限制下执行。另一方面，使用基于约束的优化方法可以生成可行的手术计划，但目前还没有机制来表示和评估复杂环境下的此类知识。为了利用现实生活应用程序所需的功能，该项目开发了一种在机器学习中嵌入约束推理的集成方法(EcoR-ML)。研究人员打算在医疗机器人的背景下证明EcoR-ML的有效性。已有的研究表明，约束推理和机器学习的结合对于这一领域的安全和高效技术的发展至关重要。该项目旨在促进机器学习和约束推理技术的发展，并将促进机器学习、约束学习和机器人领域的形式化研究和应用研究的交叉融合，为结构化领域的机器学习提供一种可扩展的方法。其核心思想是用一个表示物理和操作要求的约束推理模块来增强机器学习算法。具体地说，本研究建议在深度神经网络中嵌入决策图作为完全可区分的层，决策图是一种流行的约束推理工具。通过实施约束，生成性模型的输出现在可以提供安全性、正确性和/或公平性的保证。此外，EcoR-ML拥有比传统机器学习方法更小的建模空间，使机器学习算法学习更快，泛化得更好。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。

项目成果

Physics Knowledge Discovery via Neural Differential Equation Embedding

• DOI: 10.1007/978-3-030-86517-7_8
• 发表时间: 2021
• 作者: Yexiang Xue;M. Nasim;Maosen Zhang;C. Fan;Xinghang Zhang;A. El-Azab

Massive Text Normalization via an Efficient Randomized Algorithm

通过高效的随机算法进行海量文本标准化

• 发表时间: 2022
• 作者: Jiang, Nan;Luo, Chen;Lakshman, Vihan;Dattatreya, Yesh;Xue, Yexiang
• 通讯作者: Xue, Yexiang

Constraint Reasoning Embedded Structured Prediction

• 发表时间: 2022
• 期刊: J. Mach. Learn. Res.
• 作者: Nan Jiang;Maosen Zhang;W. V. Hoeve;Yexiang Xue

Bootstrap State Representation using Style Transfer for Better Generalization in Deep Reinforcement Learning

使用风格迁移的引导状态表示以实现深度强化学习中更好的泛化

• 发表时间: 2022
• 期刊: Proceedings of the 2022 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD
• 作者: Rahman, Md Masudur;Xue, Yexiang
• 通讯作者: Xue, Yexiang

Task Detection in Continual Learning via Familiarity Autoencoders

• DOI: 10.1109/smc53654.2022.9945326
• 发表时间: 2022-10
• 期刊: 2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)
• 作者: Maxwell J. Jacobson;Case Q. Wright;Nan Jiang;Gustavo Rodriguez-Rivera;Yexiang Xue