Neural Net Learning for Graph Data

图数据的神经网络学习

• 批准号: 2113099
• 负责人: Cencheng Shen
• 金额: $ 24万
• 依托单位: University of Delaware
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-01 至 2024-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2113099&HistoricalAwards=false
• 关键词: Neural; Net; Learning; Graph; Data

Graph structures are special data types that arise naturally in sociology, economics, public health, computer science, neuroscience, among other areas. In this project, we develop an innovative graph neural network architecture that is theoretically sound, computationally efficient, numerically superior, and versatile for a variety of graph structures. The development will incorporate many recent advances in graph embedding, dependence testing, and convolutional neural network. This project will significantly advance the theoretical foundation of graph neural networks, enable scalable and better graph learning for data scientists, and is uniquely poised to accelerate discoveries in a many graph-based applications. The project also provides research training opportunities for graduate students. In the project, the PIs will start with graph adjacency, and investigate the difference among spectral embedding, standard neural network, and a novel graph convolutional neural network. Then the PIs plan to prove that under certain graph models, the graph convolutional layer can be asymptotically Bayes optimal in supervised learning. When the graph data is further coupled with node attributes, the PIs develop an attributed neural network architecture via a distance correlation screening layer. The project aims to prove its asymptotic optimality in the presence of node attributes, investigate the relationship between graph adjacency and node attributes to enable better machine learning, and demonstrate its superior performance against existing state-of-the-art methods in simulations and real data. Moreover, the project designs the algorithm in linear-time computation complexity, making it efficient and scalable to big data and sparse graphs.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.

图形结构是社会学，经济学，公共卫生，计算机科学，神经科学等自然出现的特殊数据类型。在此项目中，我们开发了一种创新的图形神经网络体系结构，该架构在理论上是合理的，计算上有效的，数值优势和多种图形结构的。该开发将结合图形嵌入，依赖测试和卷积神经网络的许多最新进展。该项目将大大提高图形神经网络的理论基础，为数据科学家启用可扩展和更好的图形学习，并独特地准备在许多基于图基的应用程序中加速发现。该项目还为研究生提供了研究培训机会。在项目中，PI将从图形邻接开始，并研究光谱嵌入，标准神经网络和新型图卷积神经网络之间的差异。然后，PIS计划证明在某些图形模型下，图形卷积层可以渐近地贝叶斯在监督学习中最佳。当图形数据与节点属性进一步耦合时，PI通过距离相关筛选层开发归因的神经网络体系结构。该项目旨在在存在节点属性的情况下证明其渐近最优性，研究图邻接和节点属性之间的关系以启用更好的机器学习，并证明其在模拟和真实数据中现有的最新方法中的卓越性能。此外，该项目在线性时间计算复杂性中设计了算法，使其对大数据和稀疏图。该奖项反映了NSF的法定任务，并被认为是通过基金会的智力优点和更广泛的影响来通过评估来获得支持的审查标准。

项目成果

A Simple Spectral Failure Mode for Graph Convolutional Networks

• DOI: 10.1109/tpami.2021.3104733
• 发表时间: 2020-10
• 期刊: IEEE Transactions on Pattern Analysis and Machine Intelligence
• 影响因子: 23.6
• 作者: C. Priebe;Cencheng Shen;Ningyuan Huang;Tianyi Chen

One-Hot Graph Encoder Embedding

One-Hot 图编码器嵌入

• DOI: 10.1109/tpami.2022.3225073
• 发表时间: 2023
• 期刊: IEEE Transactions on Pattern Analysis and Machine Intelligence
• 影响因子: 23.6
• 作者: Shen, Cencheng;Wang, Qizhe;Priebe, Carey E.
• 通讯作者: Priebe, Carey E.