CIF: Medium: Adaptive Diffusions for Scalable and Robust Learning over Graphs
CIF:中:用于图上可扩展和鲁棒学习的自适应扩散
基本信息
- 批准号:1901134
- 负责人:
- 金额:$ 70.22万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2019
- 资助国家:美国
- 起止时间:2019-10-01 至 2023-09-30
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Behind every complex system, be it physical, social, biological, or manmade, lies an intricate network that encodes the interactions between its components. Statistical learning over networks has the potential to unleash one's ability to reason about the behavior of such systems; to understand their innate structure; and, ultimately predict their evolution. In the era of 'data deluge,' fulfilling this promise has not moved closer, as formidable challenges remain. These include making effective predictions while relying on scarce training samples; providing easily explainable outcomes in a transparent way; dealing with unreliable data or malicious attempts to undermine the learning process; as well as managing to handle massive-scale networks that can change over time in a timely and resource-considerate fashion. Aspiring to address such challenges, this project pioneers a scalable, expressive, interpretable, and robust multi-purpose framework for learning over networks. The toolbox to be developed is expected to boost state-of-the-art in data science, network science, graph mining, and big data analytics. It should thus impact and effect technology transfer to a broad range of emerging fields, from computational biology and neuroscience to social-economic networks. On the educational front, the multidisciplinary nature of this research will provide engaging experiences for both undergraduate and graduate students, disseminate research findings, and cross-fertilize ideas from diverse communities.The overarching approach in this project unifies learning over graphs under a principled framework of random walk based diffusions with the goal of markedly improving learning performance, while also ensuring scalability and reliability. The research consists of three intertwined thrusts dealing with: (T1) Adaptive diffusions for fast and effective learning over networks tuned to the task and the underlying network topology; (T2) Scalable diffusions dealing with massive and challenging networks; and (T3) Robust diffusions capable of learning from untrusted data. The novel approach in T1 capitalizes on the 'landing probabilities' of judiciously constructed random walks, and opens venues leveraging meta-information, as well as nonlinear diffusion models, in order to innovate a gamut of learning tasks over possibly dynamic graphs. The research under T2 aims at massive and challenging graphs where a prohibitively large landing probability space is necessary to ensure high prediction accuracy. Finally, T3 aspires to cope with sophisticated adversaries employing graph structure-aware approaches to infiltrate the network, and investigates lines of defense even in settings where most data are malicious. Analytical and experimental performance evaluation will assess the merits of the novel approaches relative to node embedding and graph convolutional neural network alternatives.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.
在每一个复杂的系统背后,无论是物理的、社会的、生物的还是人造的,都有一个复杂的网络,它编码了其组成部分之间的相互作用。网络上的统计学习有可能释放人们对此类系统行为的推理能力;了解它们的内在结构;并最终预测它们的进化。在“数据泛滥”的时代,实现这一承诺并没有变得更近,因为艰巨的挑战仍然存在。这些包括在依赖稀缺的训练样本的同时进行有效的预测;以透明的方式提供易于解释的结果;处理不可靠的数据或破坏学习过程的恶意尝试;以及以及时和资源考虑的方式管理可随时间变化的大规模网络。为了应对这些挑战,该项目开创了一个可扩展的,富有表现力的,可解释的和强大的多用途网络学习框架。预计将开发的工具箱将推动数据科学,网络科学,图形挖掘和大数据分析的发展。因此,它应该影响和影响从计算生物学和神经科学到社会经济网络等广泛新兴领域的技术转让。在教育方面,该研究的多学科性质将为本科生和研究生提供引人入胜的体验,传播研究成果,并从不同的社区交叉施肥的想法。该项目的总体方法将在基于随机游走扩散的原则框架下统一图形学习,目标是显着提高学习性能,同时确保可扩展性和可靠性。该研究由三个相互交织的主题组成:(T1)自适应扩散,用于在网络上快速有效地学习任务和底层网络拓扑结构;(T2)可扩展的扩散,处理大规模和具有挑战性的网络;(T3)鲁棒的扩散,能够从不可信的数据中学习。T1中的新方法利用了明智构建的随机游走的“着陆概率”,并利用元信息以及非线性扩散模型打开了场地,以便在可能的动态图上创新各种学习任务。T2下的研究针对的是大规模和具有挑战性的图形,其中需要非常大的着陆概率空间来确保高预测精度。最后,T3渴望科普使用图结构感知方法渗透网络的复杂对手,并调查即使在大多数数据都是恶意数据的情况下的防御线。分析和实验性能评估将评估新方法相对于节点嵌入和图卷积神经网络替代方案的优点。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,被认为值得支持。
项目成果
期刊论文数量(69)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Deep Policy Gradient for Reactive Power Control in Distribution Systems
- DOI:10.1109/smartgridcomm47815.2020.9302996
- 发表时间:2020-11
- 期刊:
- 影响因子:0
- 作者:Qiuling Yang;A. Sadeghi;Gang Wang;G. Giannakis;Jian Sun-
- 通讯作者:Qiuling Yang;A. Sadeghi;Gang Wang;G. Giannakis;Jian Sun-
Learning Graph Processes with Multiple Dynamical Models
- DOI:10.1109/ieeeconf44664.2019.9048993
- 发表时间:2019-11
- 期刊:
- 影响因子:0
- 作者:Qin Lu;V. Ioannidis;G. Giannakis;M. Coutiño
- 通讯作者:Qin Lu;V. Ioannidis;G. Giannakis;M. Coutiño
Bayesian Constrained Decision Fusion
贝叶斯约束决策融合
- DOI:
- 发表时间:2021
- 期刊:
- 影响因子:0
- 作者:P. A. Traganitis, G. B.
- 通讯作者:P. A. Traganitis, G. B.
Graph-Adaptive Semi-Supervised Tracking of Dynamic Processes Over Switching Network Modes
- DOI:10.1109/tsp.2020.2984889
- 发表时间:2020
- 期刊:
- 影响因子:5.4
- 作者:Qin Lu;V. Ioannidis;G. Giannakis
- 通讯作者:Qin Lu;V. Ioannidis;G. Giannakis
Efficient and Stable Graph Scattering Transforms via Pruning
- DOI:10.1109/tpami.2020.3025258
- 发表时间:2020-01
- 期刊:
- 影响因子:23.6
- 作者:V. Ioannidis;Siheng Chen;G. Giannakis
- 通讯作者:V. Ioannidis;Siheng Chen;G. Giannakis
{{
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 }}
Georgios Giannakis其他文献
Georgios Giannakis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('Georgios Giannakis', 18)}}的其他基金
Collaborative Research: ECCS-CCSS Core: Resonant-Beam based Optical-Wireless Communication
合作研究:ECCS-CCSS核心:基于谐振光束的光无线通信
- 批准号:
2332173 - 财政年份:2024
- 资助金额:
$ 70.22万 - 项目类别:
Standard Grant
Collaborative Research: CIF: Medium: Robust Learning over Graphs
协作研究:CIF:媒介:图上的鲁棒学习
- 批准号:
2312547 - 财政年份:2023
- 资助金额:
$ 70.22万 - 项目类别:
Continuing Grant
IMR: MM-1C: Learning-driven Models for 5G Internet Measurements
IMR:MM-1C:5G 互联网测量的学习驱动模型
- 批准号:
2220292 - 财政年份:2022
- 资助金额:
$ 70.22万 - 项目类别:
Standard Grant
Collaborative Research: SWIFT: Cognitive-IoV with Simultaneous Sensing and Communications via Dynamic RF Front End
合作研究:SWIFT:通过动态射频前端实现同步传感和通信的认知车联网
- 批准号:
2128593 - 财政年份:2021
- 资助金额:
$ 70.22万 - 项目类别:
Standard Grant
CCSS: Online Learning for IoT Monitoring and Management
CCSS:物联网监控和管理在线学习
- 批准号:
2126052 - 财政年份:2021
- 资助金额:
$ 70.22万 - 项目类别:
Standard Grant
Hybrid mmWave mMIMO Transceiver Design for Doubly-Selective Channels
适用于双选通道的混合毫米波 mMIMO 收发器设计
- 批准号:
2102312 - 财政年份:2020
- 资助金额:
$ 70.22万 - 项目类别:
Standard Grant
CPS: Medium: Collaborative Research: Collective Intelligence for Proactive Autonomous Driving (CI-PAD)
CPS:中:协作研究:主动自动驾驶集体智慧 (CI-PAD)
- 批准号:
2103256 - 财政年份:2020
- 资助金额:
$ 70.22万 - 项目类别:
Standard Grant
CCSS: Collaborative Research: Learn-and-Adapt to Manage Dynamic Cyber-Physical Networks
CCSS:协作研究:学习和适应管理动态信息物理网络
- 批准号:
1711471 - 财政年份:2017
- 资助金额:
$ 70.22万 - 项目类别:
Standard Grant
CCSS: Collaborative Research: Smart-Grid Powered Green Communications in Heterogeneous Networks
CCSS:协作研究:异构网络中智能电网驱动的绿色通信
- 批准号:
1508993 - 财政年份:2015
- 资助金额:
$ 70.22万 - 项目类别:
Standard Grant
EAGER-DynamicData: Judicious Censoring, Random Sketching, and Efficient Validate for Learning Patterns from Dynamically-Changing and Large-Scale Data Sets
EAGER-DynamicData:明智的审查、随机草图和高效验证,用于从动态变化的大规模数据集中学习模式
- 批准号:
1500713 - 财政年份:2015
- 资助金额:
$ 70.22万 - 项目类别:
Standard Grant
相似国自然基金
雨天动态散射介质场致激光波前畸变的时空特性及自适应抑制方法研究
- 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
跨音速流与多孔介质流耦合模型及其自适应优化算法研究
- 批准号:
- 批准年份:2022
- 资助金额:30 万元
- 项目类别:青年科学基金项目
非线性介质中光束可控变化及自适应孤子研究
- 批准号:
- 批准年份:2022
- 资助金额:30 万元
- 项目类别:地区科学基金项目
自由流与多孔介质流耦合问题的自适应虚拟元方法研究
- 批准号:12101178
- 批准年份:2021
- 资助金额:24.00 万元
- 项目类别:青年科学基金项目
新型跨介质航行器自适应运动控制研究
- 批准号:
- 批准年份:2021
- 资助金额:0.0 万元
- 项目类别:省市级项目
不可压缩流与多孔介质流耦合模型的高效数值算法研究
- 批准号:12001347
- 批准年份:2020
- 资助金额:24.0 万元
- 项目类别:青年科学基金项目
基于视觉质量驱动和域自适应学习的介质干扰图像清晰化方法
- 批准号:62071323
- 批准年份:2020
- 资助金额:54 万元
- 项目类别:面上项目
多孔储液介质仿生自适应润滑机理与结构设计研究
- 批准号:51975325
- 批准年份:2019
- 资助金额:66.0 万元
- 项目类别:面上项目
微纳孔多孔材料吸附性能及其润滑油吸附智能润滑应用探讨
- 批准号:51905297
- 批准年份:2019
- 资助金额:23.0 万元
- 项目类别:青年科学基金项目
适用于多介质湍流混合的基于物理尺度自适应的高分辨率数值方法研究
- 批准号:11801036
- 批准年份:2018
- 资助金额:25.0 万元
- 项目类别:青年科学基金项目
相似海外基金
Collaborative Research: CNS Core: Medium: Reconfigurable Kernel Datapaths with Adaptive Optimizations
协作研究:CNS 核心:中:具有自适应优化的可重构内核数据路径
- 批准号:
2345339 - 财政年份:2023
- 资助金额:
$ 70.22万 - 项目类别:
Standard Grant
Collaborative Research: CPS: Medium: Mutualistic Cyber-Physical Interaction for Self-Adaptive Multi-Damage Monitoring of Civil Infrastructure
合作研究:CPS:中:土木基础设施自适应多损伤监测的互信息物理交互
- 批准号:
2305882 - 财政年份:2023
- 资助金额:
$ 70.22万 - 项目类别:
Standard Grant
NeTS: Medium: Object-Centric, View-Adaptive and Progressive Coding and Streaming of Point Cloud Video
NeTS:Medium:以对象为中心、视图自适应和渐进式的点云视频编码和流式传输
- 批准号:
2312839 - 财政年份:2023
- 资助金额:
$ 70.22万 - 项目类别:
Continuing Grant
Collaborative Research: CSR: Medium: Adaptive Environmental Awareness for Collaborative Augmented Reality
协作研究:企业社会责任:媒介:协作增强现实的自适应环境意识
- 批准号:
2312760 - 财政年份:2023
- 资助金额:
$ 70.22万 - 项目类别:
Continuing Grant
Collaborative Research: CPS: Medium: A3EM: Animal-borne Adaptive Acoustic Environmental Monitoring
合作研究:CPS:媒介:A3EM:动物源性自适应声环境监测
- 批准号:
2312391 - 财政年份:2023
- 资助金额:
$ 70.22万 - 项目类别:
Standard Grant
AF: Medium: Concurrency and Adaptive Self-Organization in Anonymous Dynamic Networks
AF:中:匿名动态网络中的并发性和自适应自组织
- 批准号:
2312537 - 财政年份:2023
- 资助金额:
$ 70.22万 - 项目类别:
Standard Grant
Collaborative Research: CSR: Medium: Adaptive Environmental Awareness for Collaborative Augmented Reality
协作研究:企业社会责任:媒介:协作增强现实的自适应环境意识
- 批准号:
2312761 - 财政年份:2023
- 资助金额:
$ 70.22万 - 项目类别:
Continuing Grant
Collaborative Research: CSR: Medium: Adaptive Environmental Awareness for Collaborative Augmented Reality
协作研究:企业社会责任:媒介:协作增强现实的自适应环境意识
- 批准号:
2312762 - 财政年份:2023
- 资助金额:
$ 70.22万 - 项目类别:
Continuing Grant
Collaborative Research: CPS: Medium: Mutualistic Cyber-Physical Interaction for Self-Adaptive Multi-Damage Monitoring of Civil Infrastructure
合作研究:CPS:中:土木基础设施自适应多损伤监测的互信息物理交互
- 批准号:
2305883 - 财政年份:2023
- 资助金额:
$ 70.22万 - 项目类别:
Standard Grant
Collaborative Research: CPS: Medium: A3EM: Animal-borne Adaptive Acoustic Environmental Monitoring
合作研究:CPS:媒介:A3EM:动物源性自适应声环境监测
- 批准号:
2312392 - 财政年份:2023
- 资助金额:
$ 70.22万 - 项目类别:
Standard Grant