Collaborative Research: Differential Equations Motivated Multi-Agent Sequential Deep Learning: Algorithms, Theory, and Validation

协作研究:微分方程驱动的多智能体序列深度学习:算法、理论和验证

基本信息

  • 批准号:
    2152762
  • 负责人:
  • 金额:
    $ 10万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Standard Grant
  • 财政年份:
    2022
  • 资助国家:
    美国
  • 起止时间:
    2022-07-01 至 2025-06-30
  • 项目状态:
    未结题

项目摘要

Sequential data observed from multiple agents is ubiquitous in artificial intelligence (AI) and scientific applications, for example, in computer vision, natural language processing, robotics, computational biology and biophysics, and knowledge graphs. Learning from sequentially observed data often provides a global understanding of the underlying system and yields more reliable predictions than learning from a non-sequentially (single-shot) observed data. Sequential data is often irregularly-sampled in time and space and when this is combined with the interaction between agents, it raises tremendous challenges for machine learning. This project addresses these challenges by developing new mathematical understandings of these bottlenecks combined with new mathematically-principled deep learning algorithms for sequential and graph learning. Anticipated results and algorithms from this project will have broad applicability to important societal issues, such as pandemic spread, cooperative robotics, and environmental change. The project includes research training opportunities for graduate students.This project bridges ordinary differential equations (ODEs) and partial differential equations (PDEs) theory with multi-agent sequential learning practice. The project further leverages ODE and PDE insights to advance theoretically-grounded algorithms for deep sequential and graph learning. This project synergistically integrates recent advances in neural ODE methods with recent advances in graph networks for machine learning. The project develops and explores building next-generation algorithms based on wave equations on graphs, coupling second-order continuous dynamics in time with graph filtering. The research includes theoretical guarantees for the new methods in overcoming the over-smoothing issue, to enable sequential learning on graphs with deep architectures.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.
从多个代理观察到的顺序数据在人工智能(AI)和科学应用中无处不在,例如,在计算机视觉,自然语言处理,机器人,计算生物学和生物物理学以及知识图中。从连续观测数据中学习通常提供对底层系统的全局理解,并且比从非连续(单次)观测数据中学习产生更可靠的预测。序列数据通常在时间和空间上不规则地采样,当这与代理之间的交互相结合时,它给机器学习带来了巨大的挑战。该项目通过开发对这些瓶颈的新的数学理解,结合用于顺序和图学习的新的基于数学原理的深度学习算法来解决这些挑战。该项目的预期结果和算法将广泛适用于重要的社会问题,如流行病传播,合作机器人和环境变化。该项目包括研究生的研究培训机会。该项目将常微分方程(ODE)和偏微分方程(PDE)理论与多智能体顺序学习实践联系起来。该项目进一步利用ODE和PDE见解来推进深度序列和图学习的理论基础算法。该项目将神经ODE方法的最新进展与用于机器学习的图网络的最新进展协同集成。该项目开发和探索基于图形上的波动方程构建下一代算法,将二阶连续动态与图形滤波耦合在一起。 该研究包括克服过度平滑问题的新方法的理论保证,以实现对具有深度架构的图的顺序学习。该奖项反映了NSF的法定使命,并通过使用基金会的知识价值和更广泛的影响审查标准进行评估而被认为值得支持。

项目成果

期刊论文数量(5)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Implicit Graph Neural Networks: A Monotone Operator Viewpoint
  • DOI:
  • 发表时间:
    2023
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Justin Baker;Qingsong Wang;C. Hauck;Bao Wang
  • 通讯作者:
    Justin Baker;Qingsong Wang;C. Hauck;Bao Wang
Efficient and Reliable Overlay Networks for Decentralized Federated Learning
  • DOI:
    10.1137/21m1465081
  • 发表时间:
    2021-12
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Yifan Hua;Kevin Miller;A. Bertozzi;Chen Qian;Bao Wang
  • 通讯作者:
    Yifan Hua;Kevin Miller;A. Bertozzi;Chen Qian;Bao Wang
Learning Proper Orthogonal Decomposition of Complex Dynamics Using Heavy-ball Neural ODEs
使用重球神经常微分方程学习复杂动力学的正确正交分解
  • DOI:
    10.1007/s10915-023-02176-8
  • 发表时间:
    2023
  • 期刊:
  • 影响因子:
    2.5
  • 作者:
    Baker, Justin;Cherkaev, Elena;Narayan, Akil;Wang, Bao
  • 通讯作者:
    Wang, Bao
How does momentum benefit deep neural networks architecture design? A few case studies
  • DOI:
    10.1007/s40687-022-00352-0
  • 发表时间:
    2021-10
  • 期刊:
  • 影响因子:
    1.2
  • 作者:
    Bao Wang;Hedi Xia;T. Nguyen;S. Osher
  • 通讯作者:
    Bao Wang;Hedi Xia;T. Nguyen;S. Osher
Improving Deep Neural Networks’ Training for Image Classification With Nonlinear Conjugate Gradient-Style Adaptive Momentum
使用非线性共轭梯度式自适应动量改进深度神经网络 - 图像分类训练
{{ 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 }}

Bao Wang其他文献

Study on the startup characteristics of the methanogenic UASB reactor under acid condition at pH5.5
pH5.5酸性条件下产甲烷UASB反应器启动特性研究
  • DOI:
  • 发表时间:
    2013
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Bao Wang;Jie Ding;Hongjian Liu;Chunmiao Liu;Wangbin Cheng;Luyan Zhang;Xianshu Liu;Nanqi Ren
  • 通讯作者:
    Nanqi Ren
Effect of Municipal Solid Waste Incineration Fly Ash Leachate on the Hydraulic Performance of a Geosynthetic Clay Liner
城市生活垃圾焚烧飞灰渗滤液对土工合成粘土衬垫水力性能的影响
Facile fabrication of hollow CuO nanocubes for enhanced lithium/sodium storage performance
轻松制造空心 CuO 纳米立方体以增强锂/钠存储性能
  • DOI:
    10.1039/d1ce00704a
  • 发表时间:
    2021
  • 期刊:
  • 影响因子:
    3.1
  • 作者:
    Jie Zhao;Yuyan Zhao;Wen-Ce Yue;Shu-Min Zheng;Xue Li;Ning Gao;Ting Zhu;Yu-Jiao Zhang;Guang-Ming Xia;Bao Wang
  • 通讯作者:
    Bao Wang
Heterogeneous Nucleation in Semicrystalline Polymers
  • DOI:
    10.15167/wang-bao_phd2020-03-20
  • 发表时间:
    2020-03
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Bao Wang
  • 通讯作者:
    Bao Wang
The influence of wind turbine blade rotation on anemometer
风力机叶片旋转对风速计的影响
  • DOI:
    10.1088/1742-6596/2280/1/012008
  • 发表时间:
    2022
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Yaqiang Zhou;Lizhu Tian;Zhiwen Jiang;Yapeng Li;Zhaohe Wu;Chenglong Qi;Y. Gou;Yonghe Xu;Dayu Du;Bao Wang;Yuan Wu;W. Feng;Peng Li
  • 通讯作者:
    Peng Li

Bao Wang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('Bao Wang', 18)}}的其他基金

Collaborative Research: ATD: Fast Algorithms and Novel Continuous-depth Graph Neural Networks for Threat Detection
合作研究:ATD:用于威胁检测的快速算法和新颖的连续深度图神经网络
  • 批准号:
    2219956
  • 财政年份:
    2023
  • 资助金额:
    $ 10万
  • 项目类别:
    Standard Grant
Collaborative Research: Algorithms, Theory, and Validation of Deep Graph Learning with Limited Supervision: A Continuous Perspective
协作研究:有限监督下的深度图学习的算法、理论和验证:连续的视角
  • 批准号:
    2208361
  • 财政年份:
    2022
  • 资助金额:
    $ 10万
  • 项目类别:
    Continuing Grant
Student Support: 18th IEEE International Conference on eScience
学生支持:第 18 届 IEEE 国际电子科学会议
  • 批准号:
    2219510
  • 财政年份:
    2022
  • 资助金额:
    $ 10万
  • 项目类别:
    Standard Grant
Collaborative Research: ATD: Robust, Accurate and Efficient Graph-Structured RNN for Spatio-Temporal Forecasting and Anomaly Detection
合作研究:ATD:用于时空预测和异常检测的鲁棒、准确和高效的图结构 RNN
  • 批准号:
    2110145
  • 财政年份:
    2021
  • 资助金额:
    $ 10万
  • 项目类别:
    Standard Grant
Collaborative Research: ATD: Robust, Accurate and Efficient Graph-Structured RNN for Spatio-Temporal Forecasting and Anomaly Detection
合作研究:ATD:用于时空预测和异常检测的鲁棒、准确和高效的图结构 RNN
  • 批准号:
    1924935
  • 财政年份:
    2019
  • 资助金额:
    $ 10万
  • 项目类别:
    Standard Grant

相似国自然基金

Research on Quantum Field Theory without a Lagrangian Description
  • 批准号:
    24ZR1403900
  • 批准年份:
    2024
  • 资助金额:
    0.0 万元
  • 项目类别:
    省市级项目
Cell Research
  • 批准号:
    31224802
  • 批准年份:
    2012
  • 资助金额:
    24.0 万元
  • 项目类别:
    专项基金项目
Cell Research
  • 批准号:
    31024804
  • 批准年份:
    2010
  • 资助金额:
    24.0 万元
  • 项目类别:
    专项基金项目
Cell Research (细胞研究)
  • 批准号:
    30824808
  • 批准年份:
    2008
  • 资助金额:
    24.0 万元
  • 项目类别:
    专项基金项目
Research on the Rapid Growth Mechanism of KDP Crystal
  • 批准号:
    10774081
  • 批准年份:
    2007
  • 资助金额:
    45.0 万元
  • 项目类别:
    面上项目

相似海外基金

Collaborative Research: SaTC: CORE: Medium: Graph Mining and Network Science with Differential Privacy: Efficient Algorithms and Fundamental Limits
协作研究:SaTC:核心:媒介:具有差异隐私的图挖掘和网络科学:高效算法和基本限制
  • 批准号:
    2317192
  • 财政年份:
    2023
  • 资助金额:
    $ 10万
  • 项目类别:
    Continuing Grant
Collaborative Research: SaTC: CORE: Medium: Graph Mining and Network Science with Differential Privacy: Efficient Algorithms and Fundamental Limits
协作研究:SaTC:核心:媒介:具有差异隐私的图挖掘和网络科学:高效算法和基本限制
  • 批准号:
    2317194
  • 财政年份:
    2023
  • 资助金额:
    $ 10万
  • 项目类别:
    Continuing Grant
Collaborative Research: Construction and Properties of Sobolev Spaces of Differential Forms on Smooth and Lipschitz Manifolds with Applications to FEEC
合作研究:光滑流形和 Lipschitz 流形上微分形式 Sobolev 空间的构造和性质及其在 FEEC 中的应用
  • 批准号:
    2309779
  • 财政年份:
    2023
  • 资助金额:
    $ 10万
  • 项目类别:
    Standard Grant
Collaborative Research: SaTC: CORE: Medium: Graph Mining and Network Science with Differential Privacy: Efficient Algorithms and Fundamental Limits
协作研究:SaTC:核心:媒介:具有差异隐私的图挖掘和网络科学:高效算法和基本限制
  • 批准号:
    2317193
  • 财政年份:
    2023
  • 资助金额:
    $ 10万
  • 项目类别:
    Continuing Grant
Collaborative Research: Construction and Properties of Sobolev Spaces of Differential Forms on Smooth and Lipschitz Manifolds with Applications to FEEC
合作研究:光滑流形和 Lipschitz 流形上微分形式 Sobolev 空间的构造和性质及其在 FEEC 中的应用
  • 批准号:
    2309780
  • 财政年份:
    2023
  • 资助金额:
    $ 10万
  • 项目类别:
    Standard Grant
DMS-EPSRC Collaborative Research: Stability Analysis for Nonlinear Partial Differential Equations across Multiscale Applications
DMS-EPSRC 协作研究:跨多尺度应用的非线性偏微分方程的稳定性分析
  • 批准号:
    2219384
  • 财政年份:
    2022
  • 资助金额:
    $ 10万
  • 项目类别:
    Standard Grant
Collaborative Research: Differential Methods, Implicitization, and Multiplicities with a View Towards Equisingularity Theory
协作研究:以等奇性理论为视角的微分方法、隐式化和多重性
  • 批准号:
    2201149
  • 财政年份:
    2022
  • 资助金额:
    $ 10万
  • 项目类别:
    Standard Grant
Collaborative Research: Explaining Differential Success in Biodiversity Knowledge Commons
合作研究:解释生物多样性知识共享的不同成功
  • 批准号:
    2122818
  • 财政年份:
    2022
  • 资助金额:
    $ 10万
  • 项目类别:
    Standard Grant
Collaborative Research: Explaining Differential Success in Biodiversity Knowledge Commons
合作研究:解释生物多样性知识共享的不同成功
  • 批准号:
    2122819
  • 财政年份:
    2022
  • 资助金额:
    $ 10万
  • 项目类别:
    Standard Grant
Collaborative Research: Differential Equations Motivated Multi-Agent Sequential Deep Learning: Algorithms, Theory, and Validation
协作研究:微分方程驱动的多智能体序列深度学习:算法、理论和验证
  • 批准号:
    2152717
  • 财政年份:
    2022
  • 资助金额:
    $ 10万
  • 项目类别:
    Standard Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了