EAGER: An AI-driven Paradigm for Collective and Collaborative Community Resilience in the COVID-19 Era and Beyond

EAGER：COVID-19 时代及以后的集体和协作社区复原力的人工智能驱动范式

• 批准号: 2209814
• 负责人: Yanfang Ye
• 金额: $ 30万
• 依托单位: University of Notre Dame
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-11-01 至 2023-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2209814&HistoricalAwards=false
• 关键词: EAGER; AI; driven; Paradigm; Collective

The coronavirus disease (COVID-19) pandemic has exposed a critical set of vulnerabilities that have impacted community resilience in responding to escalating societal, economic, and behavioral issues. Unfortunately, there are no established solutions or proven models for us to depend on to tackle the complex challenges with significant uncertainties and unknowns. This project engages novel disciplinary perspectives to help address the devastating effects caused by COVID-19, i.e., leveraging the extracted information of experiences, ideas and support from positive-energy communities who are successfully navigating threats that can be transformed and transferred into actionable information to assist vulnerable communities to cope, progress and move forward. More specifically, by advancing artificial intelligence (AI) innovations, the goal of this project is to design and develop an AI-driven paradigm for collective and collaborative community resilience in responses to a variety of crises and exposed vulnerabilities in the COVID-19 era and beyond. With additional validation, this research will provide foundation to assist the federal and state governments, corporations, societal leaders to develop and implement strategies that will guide local and regional communities, and the nation into a successful new normal future.This exploratory yet transformative high risk-high payoff work that involves radically different approaches will have three main research components. First, the research team will construct a novel attributed heterogeneous information network (AHIN) to comprehensively model the up-to-date multi-source pandemic related data for abstract representation. Second, to understand how users interact and how information are propagated within and cross-community in social media, the team will develop an innovative nonnegative matrix factorization regularized deep graph learning model for community detection in the AHIN by considering the heterogeneity of the network. Third, the team will propose an integrated adversarial disentangler to separate the distinct, informative factors of variations hidden in the milieu to learn post embeddings for emotion and topic analysis for community classification and framing, and thus to derive supportive and constructive information for community resilience improvement. The developed AI-driven paradigm in this project will provide in-depth insights and customized guidance that can help public health experts, social workers, law enforcement, economists, and policy makers in decision-making and also enable a conceptual framework for the development of resilient community engagement strategies in responses to a variety of crises created by COVID-19 and future natural or health-related disasters. The research will be beneficial to multidisciplinary areas, including data mining, machine learning, epidemiology, economics, social and behavioral sciences. The outcomes of this project will be made publicly accessible and broadly distributed. The project will integrate research with education through curriculum development, the participation of underrepresented groups, and student mentoring activities.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.

冠状病毒病（COVID-19）大流行暴露了一系列关键的脆弱性，影响了社区应对不断升级的社会、经济和行为问题的复原力。不幸的是，我们没有既定的解决方案或经过验证的模型来应对具有重大不确定性和未知因素的复杂挑战。该项目采用新颖的学科视角，以帮助解决COVID-19造成的破坏性影响，即，利用从正能量社区中提取的经验、想法和支持信息，这些社区正在成功地应对威胁，这些威胁可以转化为可采取行动的信息，以帮助弱势社区科普、进步和向前迈进。更具体地说，通过推进人工智能（AI）创新，该项目的目标是设计和开发一个人工智能驱动的模式，以应对COVID-19时代及以后的各种危机和暴露的漏洞。通过进一步的验证，这项研究将为帮助联邦和州政府、企业、社会领导人制定和实施战略提供基础，这些战略将指导地方和区域社区以及国家进入一个成功的新常态未来。这项探索性但具有变革性的高风险高回报的工作，涉及截然不同的方法，将有三个主要的研究组成部分。首先，研究团队将构建一个新的属性异构信息网络（AHIN），以全面建模最新的多源流行病相关数据，以进行抽象表示。其次，为了了解用户如何交互以及信息如何在社交媒体中在社区内和跨社区传播，该团队将通过考虑网络的异质性，开发一种创新的非负矩阵分解正则化深度图学习模型，用于AHIN中的社区检测。第三，该团队将提出一个综合的对抗性解缠器，以分离隐藏在环境中的差异的独特的信息因素，以学习用于社区分类和框架的情感和主题分析的后嵌入，从而获得支持性和建设性的信息，以提高社区的韧性。该项目中开发的人工智能驱动范式将提供深入的见解和定制的指导，可以帮助公共卫生专家，社会工作者，执法人员，经济学家和政策制定者进行决策，并为制定弹性社区参与战略提供概念框架，以应对COVID-19造成的各种危机和未来的自然或健康相关灾害。该研究将有利于多学科领域，包括数据挖掘，机器学习，流行病学，经济学，社会和行为科学。该项目的成果将向公众开放并广泛分发。该项目将通过课程开发、代表性不足的群体的参与和学生辅导活动将研究与教育结合起来。该奖项反映了NSF的法定使命，并被认为值得通过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来支持。

项目成果

Adapting Distilled Knowledge for Few-Shot Relation Reasoning over Knowledge Graphs

采用蒸馏知识进行知识图上的少样本关系推理

• DOI: 10.1137/1.9781611977172.75
• 发表时间: 2022
• 期刊: SIAM International Conference on Data Mining (SIAM SDM
• 作者: Zhang, Yiming;Qian, Yiyue;Ye, Yanfang;Zhang, Chuxu
• 通讯作者: Zhang, Chuxu

Back-Propagating System Dependency Impact for Attack Investigation

攻击调查的反向传播系统依赖性影响

• 发表时间: 2022
• 期刊: USENIX Security Symposium
• 作者: Fang, Pengcheng;Gao, Peng;Liu, Changlin;Ayday, Erman;Jee, Kangkook;Wang, Ting;Ye, Yanfang;Liu, Zhuotao;Xiao, Xusheng
• 通讯作者: Xiao, Xusheng

Rep2Vec: Repository Embedding via Heterogeneous Graph Adversarial Contrastive Learning

• DOI: 10.1145/3534678.3539324
• 发表时间: 2022-08
• 期刊: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
• 作者: Y. Qian;Yiming Zhang;Qianlong Wen;Yanfang Ye;Chuxu Zhang

Co-Modality Graph Contrastive Learning for Imbalanced Node Classification

• 发表时间: 2022
• 作者: Y. Qian;Chunhui Zhang;Yiming Zhang;Qianlong Wen;Yanfang Ye;Chuxu Zhang

Summarizing Source Code from Structure and Context

• DOI: 10.1109/ijcnn55064.2022.9892013
• 发表时间: 2022-07
• 期刊: 2022 International Joint Conference on Neural Networks (IJCNN)
• 作者: Shifu Hou;Lingwei Chen;Yanfang Ye