CIF: Medium: Discovering Changes in Networks: Fundamental Limits, Efficient Algorithms, and Large-Scale Neuroscience

CIF：中：发现网络的变化：基本限制、高效算法和大规模神经科学

• 批准号: 1955981
• 负责人: Bobak Nazer
• 金额: $ 123.2万
• 依托单位: Trustees of Boston University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-07-01 至 2025-06-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1955981&HistoricalAwards=false
• 关键词: CIF; Medium; Discovering; Changes; Networks

Modern technological advances have made it possible to collect extremely large datasets across a wide range of disciplines, spanning from social science to neuroscience. These datasets often consist of the activity patterns of many nodes that together form a network. For instance, in a social network, each node can represent a person while a connection between two nodes can represent a friendship. In the brain, each node can represent a neuron and a connection between two nodes can represent a link between the neurons. An emerging challenge is to design algorithms that can reliably and efficiently infer the hidden structure of these networks (namely the set of connections between nodes), given only recordings of the nodes' activity patterns. A related problem seeks to identify hidden clusters or communities in a network based only on the knowledge of some of the nodes' connections. This project seeks to examine these problems from the perspective of network change discovery: Rather than attempt to recover the full network structure, the goal is to determine whether a network structure has changed significantly over a certain time scale, and where these structural changes have occurred. Preliminary findings show that, in some settings, change discovery can be substantially easier than structure recovery. This cross-disciplinary project will examine network change discovery problems from theoretical and algorithmic perspectives; the resulting tools will be applied to large neural datasets, on the way to understand how learning a task changes the connectivity of neurons in a particular region of the brain. In addition, this project will also attempt to forge new connections between the information sciences and neuroscience through a combination of focused workshops, course development, and co-supervision of undergraduate and graduate research.From a technical perspective, the goals of the project are grouped into three thrusts. The first thrust employs modern tools from information theory and high-dimensional statistics to determine the fundamental limits for testing and recovering network changes. This effort will begin with simple canonical models, such as stochastic block models and Markov random fields, where direct comparisons are possible with prior work on structure learning. It will then move towards richer models that include dynamics, partial observations, and overlapping communities. The second thrust examines these problems from an algorithmic perspective, and seeks to design computationally-efficient algorithms that can provably approach the fundamental limits established in the first thrust. These algorithms will be validated on synthetic datasets, and then adapted to handle the complexities present in real datasets. The third thrust will apply these algorithms to large-scale calcium imaging neural datasets collected from the hippocampus of mice during association and extinction learning experiments. The goal is to determine how the connectivity between neurons changes as mice learn the task.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.

现代技术的进步使收集从社会科学到神经科学的广泛学科的超大数据集成为可能。这些数据集通常由共同构成网络的许多节点的活动模式组成。例如，在社交网络中，每个节点可以代表一个人，而两个节点之间的连接可以代表友谊。在大脑中，每个节点可以代表一个神经元，两个节点之间的连接可以代表神经元之间的联系。一个新出现的挑战是设计能够可靠和高效地推断这些网络的隐藏结构(即节点之间的连接集)的算法，仅给出节点的活动模式的记录。一个相关的问题寻求仅基于一些节点连接的知识来识别网络中的隐藏簇或社区。这个项目试图从网络变化发现的角度来检查这些问题：不是试图恢复完整的网络结构，而是要确定网络结构在特定的时间范围内是否发生了重大变化，以及这些结构变化发生在哪里。初步研究结果表明，在某些情况下，变化发现比结构恢复要容易得多。这个跨学科的项目将从理论和算法的角度研究网络变化发现问题；产生的工具将应用于大型神经数据集，以了解学习任务如何改变大脑特定区域神经元的连接。此外，该项目还将尝试通过重点研讨会、课程开发以及本科生和研究生研究的共同指导，在信息科学和神经科学之间建立新的联系。从技术角度来看，该项目的目标分为三个方面。第一个推力使用信息论和高维统计中的现代工具来确定测试和恢复网络更改的基本限制。这项工作将从简单的规范模型开始，如随机块模型和马尔可夫随机场，在这些模型中，可以与先前在结构学习方面的工作进行直接比较。然后，它将转向更丰富的模型，包括动态、局部观察和重叠社区。第二个推力从算法的角度研究这些问题，并寻求设计计算效率高的算法，这些算法可以被证明接近第一个推力中建立的基本极限。这些算法将在合成数据集上进行验证，然后适应于处理真实数据集中存在的复杂性。第三个推力将把这些算法应用于从小鼠海马区收集的大规模钙成像神经数据集，这些数据集是在联想和消亡学习实验期间收集的。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势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

Scaffolding a Student to Instill Knowledge

• 发表时间: 2023
• 作者: Instill Knowledge;Anil Kag;D. A. Acar;Aditya Gangrade;Venkatesh Saligrama

Task2Sim: Towards Effective Pre-training and Transfer from Synthetic Data

• DOI: 10.1109/cvpr52688.2022.00898
• 发表时间: 2021-11
• 期刊: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 作者: Samarth Mishra;Rameswar Panda;Cheng Perng Phoo;Chun-Fu Chen;Leonid Karlinsky;Kate Saenko;Venkatesh Saligrama;R. Feris

Ideology Prediction from Scarce and Biased Supervision: Learn to Disregard the “What” and Focus on the “How”!

• DOI: 10.18653/v1/2023.acl-long.530
• 发表时间: 2023
• 作者: Chen Chen-Chen;Dylan Walker;Venkatesh Saligrama

Condensing CNNs with Partial Differential Equations

• DOI: 10.1109/cvpr52688.2022.00069
• 发表时间: 2022-06
• 期刊: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 作者: Anil Kag;Venkatesh Saligrama

Effectively Leveraging Attributes for Visual Similarity

• DOI: 10.1109/iccv48922.2021.00105
• 发表时间: 2021-05
• 期刊: 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
• 作者: Samarth Mishra;Zhongping Zhang;Yuan Shen;Ranjitha Kumar;Venkatesh Saligrama;Bryan A. Plummer