CAREER: Towards Deep Interpretable Predictions for Multi-Scope Temporal Events

职业：对多范围时间事件进行深度可解释的预测

• 批准号: 2047843
• 负责人: Yue Ning
• 金额: $ 57.19万
• 依托单位: Stevens Institute of Technology
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-06-15 至 2026-05-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2047843&HistoricalAwards=false
• 关键词: CAREER; Towards; Deep; Interpretable; Predictions

Many human events, such as personal visits to hospitals, flu outbreaks, or protests, are recorded in temporal sequences and exhibit recurring patterns. For instance, in hospital admission records, patients who have been diagnosed with hypertension often later visit the hospital for heart diseases. Predictions of human events using past event patterns are key to many stakeholders in AI-assisted decision making. Interpretable predictive models will significantly improve transparency in these decision-making processes. Recently, interpretable machine learning has been drawing an increasing amount of attention. However, most state-of-the-art works in this domain focus on static analysis such as identifying pixels for object detection in an image. Little work has been developed for temporal event prediction in dynamic, heterogeneous, and multi-source data sequences. To address this problem, this project will support the design of transformative interpretable paradigms for temporal event sequences of different scopes with heterogeneous and multi-source features. Providing predictive tools that can capture hierarchical, relational, and complex evidence will enrich and support robust forecasting in the future. This work will involve educational activities such as developing new courses on interpretable machine learning; training graduate, undergraduate, and high-school students in interdisciplinary studies; and increasing participation of women and minority groups in academic research. Core outcomes of this project such as software, datasets, and publications will be made available to the general public.This project will create a new set of interpretable mechanisms that provide dynamic, heterogeneous, and multi-source explanations in temporal event prediction. Although a variety of explainable approaches have been developed in many traditional machine learning tasks, several unique challenges remain unexplored: (1) Regulating attention-based models for auditing a model is an urgent need given the wide adoption of attention mechanisms in deep learning. (2) Most current approaches focus on selecting important input features based on correlations which often lack causal evidence. (3) Reciprocal relations and dependencies among heterogeneous data sources are largely ignored in current research. This project will address these challenges in the following ways: (i) It will investigate new collaborative attention regulation strategies by using domain knowledge for calibration. (ii) It will integrate dynamic causal discovery into temporal event prediction with hidden confounder representation learning. (iii) It will provide multi-faceted explanations by distilling semantic knowledge from unstructured text and incorporating this knowledge in a co-learning framework with multi-source temporal data. The specific research aims will be complemented by an extensive set of evaluation plans including standard retrospective evaluation on multi-scope real-world event records as well as multiple user studies to evaluate the interpretability of developed models. The project outcomes including observational data, interpretable prediction tools, and open-source software for stakeholders will be shared with the computer science research community and other practitioners in healthcare, political science, and epidemiology.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.

许多人类事件，例如对医院，流感爆发或抗议活动的个人访问，都记录在时间序列中并展示反复出现的模式。例如，在医院入院记录中，被诊断出患有高血压的患者经常以后访问医院的心脏病医院。使用过去的事件模式对人类事件的预测是许多利益相关者在AI辅助决策中的关键。可解释的预测模型将显着提高这些决策过程中的透明度。最近，可解释的机器学习一直在引起越来越多的关注。但是，大多数最新的域名都在该领域工作着重于静态分析，例如识别图像中的对象检测像素。对于动态，异质和多源数据序列的时间事件预测，几乎没有开发工作。为了解决这个问题，该项目将支持具有异质和多源功能的不同范围的时间事件序列的变换性可解释范式的设计。提供可以捕获层次，关系和复杂证据的预测工具将在未来丰富和支持强大的预测。这项工作将涉及教育活动，例如开发有关可解释的机器学习的新课程；培训毕业生，本科和高中生跨学科研究；妇女和少数群体参与学术研究。该项目的核心结果，例如软件，数据集和出版物，将提供给公众。此项目将创建一套新的可解释机制，这些机制在时间事件预测中提供动态，异构和多源说明。尽管在许多传统的机器学习任务中已经开发了各种可解释的方法，但仍未探索几个独特的挑战：（1）鉴于深度学习中关注机制的广泛采用，调节基于注意力的模型进行审核是迫切需要的。 （2）大多数当前方法都集中在基于通常缺乏因果证据的相关性的相关性上选择重要的输入特征。 （3）当前研究中，异质数据源之间的相互关系和依赖关系在很大程度上被忽略了。该项目将以以下方式解决这些挑战：（i）它将通过使用域知识进行校准来研究新的协作注意调节策略。 （ii）它将将动态因果发现与隐藏的混杂表示的学习整合到时间事件预测中。 （iii）它将通过将语义知识从非结构化的文本中提炼出来，并将这些知识纳入与多源时间数据的共同学习框架中，从而提供多方面的解释。特定的研究目的将通过一系列广泛的评估计划进行补充，包括对多范围真实世界事件记录的标准回顾性评估以及评估开发模型的可解释性的多个用户研究。该项目的结果包括观察数据，可解释的预测工具和针对利益相关者的开源软件，将与计算机科学研究社区和其他医疗保健，政治学和流行病学领域的其他从业人员共享。该奖项反映了NSF的法定任务，并通过基金会的知识优点和广泛的影响来通过评估来评估NSF的法定任务。

项目成果

FairLP: Towards Fair Link Prediction on Social Network Graphs

FairLP：迈向社交网络图上的公平链接预测

• DOI: 10.1609/icwsm.v16i1.19321
• 发表时间: 2022
• 期刊: Proceedings of the International AAAI Conference on Web and Social Media
• 作者: Li, Yanying;Wang, Xiuling;Ning, Yue;Wang, Hui
• 通讯作者: Wang, Hui

Context-aware Health Event Prediction via Transition Functions on Dynamic Disease Graphs

• DOI: 10.1609/aaai.v36i4.20380
• 发表时间: 2021-12
• 期刊: ArXiv
• 作者: Chang Lu;Tian Han;Yue Ning

Text-enhanced Multi-Granularity Temporal Graph Learning for Event Prediction

• DOI: 10.1109/icdm54844.2022.00027
• 发表时间: 2022-01-01
• 期刊: 2022 IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM)
• 作者: Han，Xiaoxue;Ning，Yue
• 通讯作者: Ning，Yue

Algorithmic fairness in computational medicine.

• DOI: 10.1016/j.ebiom.2022.104250
• 发表时间: 2022-10
• 期刊: EBIOMEDICINE
• 影响因子: 11.1
• 作者: Xu, Jie;Xiao, Yunyu;Wang, Wendy Hui;Ning, Yue;Shenkman, Elizabeth A.;Bian, Jiang;Wang, Fei
• 通讯作者: Wang, Fei

Robust Event Forecasting with Spatiotemporal Confounder Learning

• DOI: 10.1145/3534678.3539427
• 发表时间: 2022-08
• 期刊: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
• 作者: Songgaojun Deng;H. Rangwala;Yue Ning