Collaborative Research: Towards a Theoretic Foundation for Optimal Deep Graph Learning
协作研究:为最优深度图学习奠定理论基础
基本信息
- 批准号:2134081
- 负责人:
- 金额:$ 35万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Continuing Grant
- 财政年份:2022
- 资助国家:美国
- 起止时间:2022-01-01 至 2024-12-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Graph learning has become the cornerstone in numerous real-world applications, such as social media mining, brain connectivity analysis, computational epidemiology and financial fraud detection. Graph neural networks (GNNs for short) represent an important and emerging family of deep graph learning models. By producing a vector representation of graph elements, GNNs have largely streamlined a multitude of graph learning problems. In the vast majority of the existing works, they require a given graph, including its topology, the associated attribute information and labels for (semi-)supervised learning tasks, as part of the input of the corresponding learning model. Despite tremendous progress being made, a theoretical foundation of optimal deep graph learning is still missing, a gap that this project aims to fulfill. The outcomes of this project have broader impacts on education and society. The results of this project enrich the curriculum as well as summer outreach programs at participating institutions, and are further disseminated to the community through a variety of formats to create synergies and advance understandings of different disciplines. This project benefits a variety of high-impact graph learning based applications, including recommendation, power grid, neural science, team science and management, and intelligent transportation systems.This project examines the fundamental role of the input data, including graph topology, attributes and optional labels, in graph neural networks. There are three research thrusts in this project. The first thrust seeks to understand how sensitive the GNNs model is with respect to the input graph; how to quantify the uncertainty of the GNNs model; and how that impacts the generalization performance of the GNNs model. The second thrust develops algorithms to optimize the initially provided graph so as to maximally boost the generalization performance of the given GNNs model. The third thrust develops active learning methods based on deep reinforcement learning with entropy regularization to optimally obtain the additional labels to further improve the GNNs model. This project investigates new theoretic foundations in terms of the sensitivity, the uncertainty and the generalization performance of graph neural networks. It develops new algorithms for learning optimal graphs and active GNNs with better efficacy whose fundamental limits, including sample complexity, generalization error bound, optimality and convergence rate, are well understood.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.
图学习已经成为许多现实世界应用的基石,例如社交媒体挖掘,大脑连接分析,计算流行病学和金融欺诈检测。图神经网络(简称GNN)代表了一个重要的新兴的深度图学习模型家族。通过生成图元素的矢量表示,GNN在很大程度上简化了大量的图学习问题。在绝大多数现有作品中,它们需要给定的图,包括其拓扑结构、相关的属性信息和(半)监督学习任务的标签,作为相应学习模型输入的一部分。尽管取得了巨大的进展,但最佳深度图学习的理论基础仍然缺失,这是该项目旨在填补的空白。该项目的成果对教育和社会产生了更广泛的影响。该项目的成果丰富了参与机构的课程和夏季外展计划,并通过各种形式进一步传播给社区,以产生协同作用并促进对不同学科的理解。该项目将为各种高影响力的基于图学习的应用提供帮助,包括推荐、电网、神经科学、团队科学和管理以及智能交通系统。该项目将研究输入数据在图神经网络中的基本作用,包括图的拓扑结构、属性和可选标签。在这个项目中有三个研究重点。第一个目标是了解GNNs模型对输入图的敏感程度;如何量化GNNs模型的不确定性;以及这如何影响GNNs模型的泛化性能。第二个推力开发算法来优化最初提供的图,以便最大限度地提高给定GNNs模型的泛化性能。第三个目标是开发基于深度强化学习和熵正则化的主动学习方法,以最佳方式获得额外的标签,从而进一步改进GNNs模型。本计画针对图类神经网路的灵敏度、不确定性与泛化性能,探讨新的理论基础。它开发了新的算法,用于学习最优图和主动GNN,具有更好的效率,其基本限制,包括样本复杂性,泛化误差界,最优性和收敛速度,都得到了很好的理解。该奖项反映了NSF的法定使命,并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,被认为值得支持。
项目成果
期刊论文数量(3)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Batch Active Learning with Graph Neural Networks via Multi-Agent Deep Reinforcement Learning
- DOI:10.1609/aaai.v36i8.20897
- 发表时间:2022-06
- 期刊:
- 影响因子:0
- 作者:Yuheng Zhang;Hanghang Tong;Yinglong Xia;Yan Zhu-;Yuejie Chi;Lei Ying
- 通讯作者:Yuheng Zhang;Hanghang Tong;Yinglong Xia;Yan Zhu-;Yuejie Chi;Lei Ying
Active Heterogeneous Graph Neural Networks with Per-step Meta-Q-Learning
- DOI:10.1109/icdm54844.2022.00176
- 发表时间:2022-11
- 期刊:
- 影响因子:0
- 作者:Yuheng Zhang;Yinglong Xia;Yan Zhu;Yuejie Chi;Lei Ying;H. Tong
- 通讯作者:Yuheng Zhang;Yinglong Xia;Yan Zhu;Yuejie Chi;Lei Ying;H. Tong
Provably Efficient Model-Free Algorithms for Non-stationary CMDPs
- DOI:10.48550/arxiv.2303.05733
- 发表时间:2023-03
- 期刊:
- 影响因子:0
- 作者:Honghao Wei;A. Ghosh;N. Shroff;Lei Ying;Xingyu Zhou
- 通讯作者:Honghao Wei;A. Ghosh;N. Shroff;Lei Ying;Xingyu Zhou
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Lei Ying其他文献
YY1 deficiency in beta-cells leads to mitochondrial dysfunction and diabetes in mice
β细胞中的YY1缺陷导致小鼠线粒体功能障碍和糖尿病
- DOI:
10.1016/j.metabol.2020.154353 - 发表时间:
2020 - 期刊:
- 影响因子:9.8
- 作者:
Song Dalong;Yang Qi;Jiang Xiuli;Shan Aijing;Nan Jingminjie;Lei Ying;Ji He;Di Wei;Yang Tianxiao;Wang Tiange;Wang Weiqing;Ning Guang;Cao Yanan - 通讯作者:
Cao Yanan
Data fusion based EKF-UI for real-time simultaneous identification of structural systems and unknown external inputs
基于数据融合的 EKF-UI,用于结构系统和未知外部输入的实时同步识别
- DOI:
10.1016/j.measurement.2016.02.002 - 发表时间:
2016-06 - 期刊:
- 影响因子:5.6
- 作者:
Liu Lijun;Su Ying;Zhu Jiajia;Lei Ying - 通讯作者:
Lei Ying
Improving the Electroluminescent Performance of Blue Light-Emitting Polymers by Side-Chain Modification
通过侧链修饰提高蓝光聚合物的电致发光性能
- DOI:
10.1021/acsami.9b21652 - 发表时间:
2020 - 期刊:
- 影响因子:9.5
- 作者:
Feng Peng;Wenkai Zhong;Zhiming Zhong;Ting Guo;Lei Ying - 通讯作者:
Lei Ying
Sodium arsenite augments sensitivity of Echinococcus granulosus protoscoleces to albendazole.
亚砷酸钠增强细粒棘球绦虫原头节对阿苯达唑的敏感性。
- DOI:
10.1016/j.exppara.2019.02.008 - 发表时间:
2019-05 - 期刊:
- 影响因子:2.1
- 作者:
Xing Guoqiang;Zhang Hui;Liu Chunli;Guo Zhengyi;Yang Xiaoli;Wang Zhuo;Wang Bo;Lei Ying;Yang Rentan;Jian Yufeng;Lv Hailong - 通讯作者:
Lv Hailong
Erythromycin relaxes BALB/c mouse airway smooth muscle
红霉素松弛 BALB/c 小鼠气道平滑肌
- DOI:
10.1016/j.lfs.2019.02.009 - 发表时间:
2019-03 - 期刊:
- 影响因子:6.1
- 作者:
Cai Yan;Lei Ying;Chen Jingguo;Cao Lei;Yang Xudong;Zhang Kanghuai;Cao Yongxiao - 通讯作者:
Cao Yongxiao
Lei Ying的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Lei Ying', 18)}}的其他基金
Collaborative Research: III: Small: Reconstruction of Diffusion History in Cyber and Human Networks with Applications in Epidemiology and Cybersecurity
合作研究:III:小:重建网络和人类网络中的扩散历史及其在流行病学和网络安全中的应用
- 批准号:
2324769 - 财政年份:2023
- 资助金额:
$ 35万 - 项目类别:
Standard Grant
Collaborative Research: SLES: Safe Distributional-Reinforcement Learning-Enabled Systems: Theories, Algorithms, and Experiments
协作研究:SLES:安全的分布式强化学习系统:理论、算法和实验
- 批准号:
2331780 - 财政年份:2023
- 资助金额:
$ 35万 - 项目类别:
Standard Grant
Collaborative Research: CIF: Small: Nonasymptotic Analysis for Stochastic Networks and Systems: Foundations and Applications
合作研究:CIF:小型:随机网络和系统的非渐近分析:基础和应用
- 批准号:
2207548 - 财政年份:2022
- 资助金额:
$ 35万 - 项目类别:
Standard Grant
NeTS: Small: Collaborative Research: Towards Adaptive and Efficient Wireless Computing Networks
NeTS:小型:协作研究:迈向自适应且高效的无线计算网络
- 批准号:
2002608 - 财政年份:2019
- 资助金额:
$ 35万 - 项目类别:
Standard Grant
III: Small: Towards a Theoretical Foundation for Diffusion Source Localization
III:小:迈向扩散源定位的理论基础
- 批准号:
2003924 - 财政年份:2019
- 资助金额:
$ 35万 - 项目类别:
Standard Grant
SpecEES: Collaborative Research: Leveraging Randomization and Human Behavior for Efficient Large-Scale Distributed Spectrum Access
SpecEES:协作研究:利用随机化和人类行为实现高效的大规模分布式频谱访问
- 批准号:
2001687 - 财政年份:2019
- 资助金额:
$ 35万 - 项目类别:
Standard Grant
NeTS: Small: Collaborative Research: Towards Adaptive and Efficient Wireless Computing Networks
NeTS:小型:协作研究:迈向自适应且高效的无线计算网络
- 批准号:
1813392 - 财政年份:2018
- 资助金额:
$ 35万 - 项目类别:
Standard Grant
SpecEES: Collaborative Research: Leveraging Randomization and Human Behavior for Efficient Large-Scale Distributed Spectrum Access
SpecEES:协作研究:利用随机化和人类行为实现高效的大规模分布式频谱访问
- 批准号:
1824393 - 财政年份:2018
- 资助金额:
$ 35万 - 项目类别:
Standard Grant
III: Small: Towards a Theoretical Foundation for Diffusion Source Localization
III:小:迈向扩散源定位的理论基础
- 批准号:
1715385 - 财政年份:2017
- 资助金额:
$ 35万 - 项目类别:
Standard Grant
Collaborative Research: Resource Allocation for Time-Critical Communications in Wireless Networks
合作研究:无线网络中时间关键型通信的资源分配
- 批准号:
1609202 - 财政年份:2016
- 资助金额:
$ 35万 - 项目类别:
Standard Grant
相似国自然基金
复杂电子产品超精密加工及检测关键技术研究与应用
- 批准号:
- 批准年份:2025
- 资助金额:0.0 万元
- 项目类别:省市级项目
基于合成生物学的动物底盘品种优化及中试应用研究
- 批准号:
- 批准年份:2025
- 资助金额:0.0 万元
- 项目类别:省市级项目
运用组学整合技术探索萆薢分清散联合化疗治疗晚期胰腺癌的临床研究
- 批准号:
- 批准年份:2025
- 资助金额:0.0 万元
- 项目类别:省市级项目
九里香等提取物多靶向制剂抗肺癌的作用及机制研究
- 批准号:
- 批准年份:2025
- 资助金额:0.0 万元
- 项目类别:省市级项目
升血小板方治疗原发免疫性血小板减少症的临床研究
- 批准号:
- 批准年份:2025
- 资助金额:0.0 万元
- 项目类别:省市级项目
八髎穴微波热疗在女性膀胱过度活动症治疗中的价值研究
- 批准号:
- 批准年份:2025
- 资助金额:0.0 万元
- 项目类别:省市级项目
基于 miR-455-5p 介导的氧化应激机制探讨糖尿病视网膜病变中医分型治疗的临床研究
- 批准号:
- 批准年份:2025
- 资助金额:0.0 万元
- 项目类别:省市级项目
基于 UPLC-Q-TOF-MS/MS 分析的 异功散活性成分评价及提取工艺研究
- 批准号:
- 批准年份:2025
- 资助金额:0.0 万元
- 项目类别:省市级项目
无创电针对于痉挛型双瘫脑 瘫患儿的有效性与安全性研究:一项随机 单盲前瞻性队列研究
- 批准号:
- 批准年份:2025
- 资助金额:0.0 万元
- 项目类别:省市级项目
弹压式手法与体外冲击波治疗肱骨外上髁炎的对比研究
- 批准号:
- 批准年份:2025
- 资助金额:0.0 万元
- 项目类别:省市级项目
相似海外基金
Collaborative Research: Maritime to Inland Transitions Towards ENvironments for Convection Initiation (MITTEN CI)
合作研究:海洋到内陆向对流引发环境的转变(MITTEN CI)
- 批准号:
2349935 - 财政年份:2024
- 资助金额:
$ 35万 - 项目类别:
Continuing Grant
Collaborative Research: Maritime to Inland Transitions Towards ENvironments for Convection Initiation (MITTEN CI)
合作研究:海洋到内陆向对流引发环境的转变(MITTEN CI)
- 批准号:
2349934 - 财政年份:2024
- 资助金额:
$ 35万 - 项目类别:
Continuing Grant
Collaborative Research: Frameworks: MobilityNet: A Trustworthy CI Emulation Tool for Cross-Domain Mobility Data Generation and Sharing towards Multidisciplinary Innovations
协作研究:框架:MobilityNet:用于跨域移动数据生成和共享以实现多学科创新的值得信赖的 CI 仿真工具
- 批准号:
2411152 - 财政年份:2024
- 资助金额:
$ 35万 - 项目类别:
Standard Grant
Collaborative Research: Maritime to Inland Transitions Towards ENvironments for Convection Initiation (MITTEN CI)
合作研究:海洋到内陆向对流引发环境的转变(MITTEN CI)
- 批准号:
2349936 - 财政年份:2024
- 资助金额:
$ 35万 - 项目类别:
Continuing Grant
Collaborative Research: Multiple Team Membership (MTM) through Technology: A path towards individual and team wellbeing?
协作研究:通过技术实现多重团队成员 (MTM):通往个人和团队福祉的道路?
- 批准号:
2345652 - 财政年份:2024
- 资助金额:
$ 35万 - 项目类别:
Standard Grant
Collaborative Research: Frameworks: MobilityNet: A Trustworthy CI Emulation Tool for Cross-Domain Mobility Data Generation and Sharing towards Multidisciplinary Innovations
协作研究:框架:MobilityNet:用于跨域移动数据生成和共享以实现多学科创新的值得信赖的 CI 仿真工具
- 批准号:
2411153 - 财政年份:2024
- 资助金额:
$ 35万 - 项目类别:
Standard Grant
Collaborative Research: Maritime to Inland Transitions Towards ENvironments for Convection Initiation (MITTEN CI)
合作研究:海洋到内陆向对流引发环境的转变(MITTEN CI)
- 批准号:
2349937 - 财政年份:2024
- 资助金额:
$ 35万 - 项目类别:
Continuing Grant
Collaborative Research: Multiple Team Membership (MTM) through Technology: A path towards individual and team wellbeing?
协作研究:通过技术实现多重团队成员 (MTM):通往个人和团队福祉的道路?
- 批准号:
2345651 - 财政年份:2024
- 资助金额:
$ 35万 - 项目类别:
Standard Grant
Collaborative Research: Frameworks: MobilityNet: A Trustworthy CI Emulation Tool for Cross-Domain Mobility Data Generation and Sharing towards Multidisciplinary Innovations
协作研究:框架:MobilityNet:用于跨域移动数据生成和共享以实现多学科创新的值得信赖的 CI 仿真工具
- 批准号:
2411151 - 财政年份:2024
- 资助金额:
$ 35万 - 项目类别:
Standard Grant
Collaborative Research: SaTC: CORE: Small: Towards Secure and Trustworthy Tree Models
协作研究:SaTC:核心:小型:迈向安全可信的树模型
- 批准号:
2413046 - 财政年份:2024
- 资助金额:
$ 35万 - 项目类别:
Standard Grant