Collaborative Research: RI: AF: Medium: Exchanging Knowledge Beyond Data Between Human and Machine Learner

协作研究：RI：AF：媒介：在人类和机器学习者之间交换数据之外的知识

• 批准号: 1956441
• 负责人: Guy Van den Broeck
• 金额: $ 49.89万
• 依托单位: University of California-Los Angeles
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-10-01 至 2023-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1956441&HistoricalAwards=false
• 关键词: Collaborative; Research; RI; AF; Medium

Recent advances in deep learning have made dramatic progress in solving basic perceptual tasks such as speech recognition and object detection. To pave the way for the many human-centered applications that these advances might enable, in healthcare for instance, it is important to move beyond classification problems: to think of machine learning systems as producing not just category predictions, but also the reasons for them. Moreover, these patterns of reasoning need to be comprehensible to humans. To enable this, this project will focus on the exchange of knowledge between humans and machine learning systems and how such exchange of knowledge beyond data can lead to better predictions that are also human-interpretable. The project will result in technological advances that will have the potential to significantly impact the usability of machine learning in human-facing applications.The technical aims of this project are developed along two broad themes. The first addresses the question, "How can we involve human feedback in the machine learning process to create succinct models that are interpretable and generate predictions that are explainable?" By enabling humans to provide rich feedback in the form of rules-of-thumb as relational knowledge, the project aims to derive succinct interpretable machine learning models that are amenable to simple explanations that are more compatible with the causal world-view of humans. To enhance the interpretability of machine learning, the project will further explore how human feedback based on relational knowledge can be leveraged to reduce the size of data sets required to train accurate models. The second addresses the question, "How can we encode and exploit relational information in deriving interpretable and explainable models for reasoning?" The project will explore the encoding of relational knowledge in both vector spaces and logical models and further investigate how relational knowledge can be used for analogical reasoning, semantic understanding, and relational queries.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.

深度学习的最新进展在解决语音识别和物体检测等基本感知任务方面取得了巨大进展。为了为这些进步可能实现的许多以人为中心的应用铺平道路，例如在医疗保健领域，重要的是超越分类问题：将机器学习系统视为不仅产生类别预测，而且还产生它们的原因。此外，这些推理模式需要为人类所理解。为了实现这一目标，该项目将重点关注人类和机器学习系统之间的知识交换，以及这种数据之外的知识交换如何能够带来更好的人类可解释的预测。该项目将带来技术进步，有可能对机器学习在面向人类的应用中的可用性产生重大影响。该项目的技术目标围绕两大主题制定。第一个解决了这样的问题：“我们如何将人类反馈纳入机器学习过程中，以创建可解释的简洁模型并生成可解释的预测？”通过使人类能够以经验法则的形式提供丰富的反馈作为关系知识，该项目旨在导出简洁的可解释的机器学习模型，这些模型适合于更符合人类因果世界观的简单解释。为了增强机器学习的可解释性，该项目将进一步探索如何利用基于关系知识的人类反馈来减少训练准确模型所需的数据集的大小。第二个问题解决了“我们如何编码和利用关系信息来导出可解释和可解释的推理模型？”该项目将探索向量空间和逻辑模型中关系知识的编码，并进一步研究如何将关系知识用于类比推理、语义理解和关系查询。该奖项反映了 NSF 的法定使命，并被认为值得通过以下方式获得支持：使用基金会的智力价值和更广泛的影响审查标准进行评估。

项目成果

SIMPLE: A Gradient Estimator for k-subset sampling

简单：用于 k 子集采样的梯度估计器

• 发表时间: 2023
• 期刊: Proceedings of the International Conference on Learning Representations (ICLR
• 作者: Ahmed, Kareem;Zeng, Zhe;Niepert, Mathias;Van den Broeck, Guy
• 通讯作者: Van den Broeck, Guy

Emergent analogical reasoning in large language models

• DOI: 10.1038/s41562-023-01659-w
• 发表时间: 2022-12
• 期刊: Nature Human Behaviour
• 影响因子: 29.9
• 作者: Taylor W. Webb;K. Holyoak;Hongjing Lu

Neuro-Symbolic Entropy Regularization

神经符号熵正则化

• 发表时间: 2022
• 期刊: Proceedings of the 38th Conference on Uncertainty in Artificial Intelligence (UAI
• 作者: Ahmed, K.;Wang, E.;Chang, KW.;Van den Broeck, G.
• 通讯作者: Van den Broeck, G.

Pylon: A PyTorch Framework for Learning with Constraints

Pylon：用于约束学习的 PyTorch 框架

• DOI: 10.1609/aaai.v36i11.21711
• 发表时间: 2022
• 期刊: Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track
• 作者: Ahmed, Kareem;Li, Tao;Ton, Thy;Guo, Quan;Chang, Kai-Wei;Kordjamshidi, Parisa;Srikumar, Vivek;Van den Broeck, Guy;Singh, Sameer
• 通讯作者: Singh, Sameer

A Pseudo-Semantic Loss for Deep Generative Models with Logical Constraints

具有逻辑约束的深度生成模型的伪语义损失

• 发表时间: 2023
• 期刊: Advances in Neural Information Processing Systems 36 (NeurIPS
• 作者: Ahmed, Kareem;Chang, Kai-Wei;Van den Broeck, Guy
• 通讯作者: Van den Broeck, Guy