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：
Georgios Giannakis
金额：
$ 70.22万
依托单位：
University of Minnesota-Twin Cities
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：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1901134&HistoricalAwards=false
关键词：
CIF Medium Adaptive Diffusions Scalable

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.

在每个复杂系统的背后，无论是物理，社会，生物学还是人造的，都是一个复杂的网络，该网络编码其组件之间的相互作用。网络上的统计学习有可能释放一个人对此类系统行为的推理的能力；了解他们的先天结构；并且，最终预测了它们的演变。在“数据洪水”的时代，履行这一诺言并没有更加紧密，因为仍然存在巨大的挑战。这些包括在依靠稀缺训练样本的同时做出有效的预测；以透明的方式提供易于解释的结果；处理不可靠的数据或恶意尝试破坏学习过程；以及设法处理大规模的网络，这些网络可以随着时间的流逝而改变，以及时和资源考虑。为了应对这些挑战，该项目开创了一个可扩展，表现力，可解释和强大的多功能框架，用于通过网络学习。预计要开发的工具箱将促进数据科学，网络科学，图形挖掘和大数据分析方面的最先进。因此，它应该影响和影响技术转移到从计算生物学和神经科学到社会经济网络的广泛新兴领域。在教育方面，这项研究的跨学科性质将为本科生和研究生提供引人入胜的经验，传播研究结果，并从不同社区中的思想进行交叉剥夺。该项目中的总体方法可以在基于随机步行的范围内的图表上进行学习，从而在基于随机步行的框架下具有明显的基于步行的范围，同时提高了学习的性能，同时又可以提高学习性能，并可靠地进行性能，并可靠地进行性能。该研究由三个相互交织的推力组成：（T1）自适应扩散，用于对任务和基础网络拓扑的网络的快速有效学习；（T2）涉及大量和具有挑战性的网络的可扩展扩散；（T3）能够从不受信任的数据中学习的强大扩散。 T1中的新颖方法利用了明智地构建的随机步行的“着陆概率”，并打开了利用元信息以及非线性扩散模型的场所，以创新一系列学习任务，超过可能动态图。 T2下的研究旨在实现巨大而挑战性的图表，在这些图表中，有必要大大的着陆概率空间以确保高预测准确性。最后，T3渴望应对采用图形结构感知方法渗透网络的复杂对手，即使在大多数数据是恶意的情况下，也可以调查防御线。分析和实验性能评估将评估相对于节点嵌入和图形卷积神经网络替代方案的新方法的优点。该奖项反映了NSF的法定任务，并被认为是值得通过基金会的智力优点和更广泛影响的评估来评估值得支持的。

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）

Learning Graph Processes with Multiple Dynamical Models

DOI：
10.1109/ieeeconf44664.2019.9048993
发表时间：
2019-11
期刊：
2019 53rd Asilomar Conference on Signals, Systems, and Computers
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

Deep Policy Gradient for Reactive Power Control in Distribution Systems

DOI：
10.1109/smartgridcomm47815.2020.9302996
发表时间：
2020-11
期刊：
2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)
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-

Graph-Adaptive Semi-Supervised Tracking of Dynamic Processes Over Switching Network Modes