III: Small: Collaborative Research: Demystifying Deep Learning on Graphs: From Basic Operations to Applications

III：小：协作研究：揭秘图深度学习：从基本操作到应用

基本信息

批准号：
2006861
负责人：
Shuiwang Ji
金额：
$ 23.13万
依托单位：
Texas A&M Engineering Experiment Station
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2020
资助国家：
美国
起止时间：
2020-10-01 至 2024-09-30
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=2006861&HistoricalAwards=false
关键词：
III Small Collaborative Research Demystifying

项目摘要

Graphs are ubiquitous in myriad high-impact domains, e.g., social media platforms, collaboration networks, biological networks, and critical infrastructure systems. Recent years have witnessed a surge of research interests in developing deep learning algorithms (in particular graph convolution networks - GCNs) for graph data. By stacking multiple layers of neural network primitives, GCNs learn high-level feature representations and address graph-related applications in an end-to-end manner, achieving superior performance in various learning tasks. In particular, the graph convolution and graph pooling operations are considered as fundamental building blocks of GCNs. However, a vast majority of existing graph convolution and graph pooling operations are simple extensions of the corresponding operations from convolution neural networks. Therefore, they are insufficient to tackle the fundamental challenges brought by real-world graphs and advance high-impact graph mining applications. The primary goal of this project is to develop novel operations to improve the essential building blocks of deep learning algorithms for graphs, propelling the state-of-the-art graph mining and deep learning research to a new frontier and advancing graph-related applications from different disciplines.This project proposes a class of novel graph convolution and pooling operations that can faithfully characterize the properties of real-world graphs from different perspectives, and build more tailored and powerful deep architectures in handling high-impact graph applications from different domains. First, it develops a family of trainable graph convolution operations that can integrate properties of real-world graphs from different aspects at the feature-level, edge-level, and node-level. Second, it investigates the problem of graph pooling to support graph-level analytical tasks and develops novel topology-aware graph pooling operations based on node sampling and node clustering. Third, it assesses the impact of proposed graph convolution and graph pooling operations by building more powerful and customized deep learning architectures for various common graph applications, such as graph anomaly detection and graph alignment. This project will be tightly integrated with newly developed undergraduate and graduate courses. The results and findings of this project will be disseminated through public datasets, open-source software repositories, journal and conference publications, special-purpose workshops or tutorials, as well as education and outreach activities.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.

图在无数高影响力领域中无处不在，例如社交媒体平台、协作网络、生物网络和关键基础设施系统。近年来，人们对开发图数据深度学习算法（特别是图卷积网络 - GCN）的研究兴趣激增。通过堆叠多层神经网络原语，GCN 学习高级特征表示并以端到端的方式处理与图相关的应用，从而在各种学习任务中实现卓越的性能。特别是，图卷积和图池化操作被认为是 GCN 的基本构建块。然而，绝大多数现有的图卷积和图池化操作都是卷积神经网络相应操作的简单扩展。因此，它们不足以解决现实世界图带来的根本挑战并推进高影响力的图挖掘应用程序。该项目的主要目标是开发新颖的操作来改进图深度学习算法的基本构建模块，将最先进的图挖掘和深度学习研究推向新的前沿，并从该项目提出了一类新颖的图卷积和池化操作，可以从不同的角度忠实地表征现实世界图的属性，并构建更定制和更强大的深层架构来处理来自不同领域的高影响力的图应用。首先，它开发了一系列可训练的图卷积运算，可以从特征级、边级和节点级的不同方面集成现实世界图的属性。其次，它研究了图池化问题以支持图级分析任务，并开发了基于节点采样和节点聚类的新颖的拓扑感知图池化操作。第三，它通过为各种常见的图应用（例如图异常检测和图对齐）构建更强大和定制的深度学习架构来评估所提出的图卷积和图池操作的影响。该项目将与新开发的本科生和研究生课程紧密结合。该项目的成果和发现将通过公共数据集、开源软件存储库、期刊和会议出版物、特殊用途研讨会或教程以及教育和外展活动进行传播。该奖项反映了 NSF 的法定使命，并被视为值得通过使用基金会的智力优点和更广泛的影响审查标准进行评估来支持。

项目成果

期刊论文数量（10）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Topology-Aware Graph Pooling Networks

DOI：
10.1109/tpami.2021.3062794
发表时间：
2021-12-01
期刊：
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
影响因子：
23.6
作者：
Gao, Hongyang;Liu, Yi;Ji, Shuiwang
通讯作者：
Ji, Shuiwang

Neighbor2Seq: Deep Learning on Massive Graphs by Transforming Neighbors to Sequences

DOI：
10.1137/1.9781611977172.7
发表时间：
2022-02
期刊：
影响因子：
0
作者：
Meng Liu;Shuiwang Ji
通讯作者：
Meng Liu;Shuiwang Ji

Efficient and Equivariant Graph Networks for Predicting Quantum Hamiltonian

DOI：
10.48550/arxiv.2306.04922
发表时间：
2023-06
期刊：
影响因子：
0
作者：
Haiyang Yu;Zhao Xu;X. Qian;Xiaoning Qian;Shuiwang Ji
通讯作者：
Haiyang Yu;Zhao Xu;X. Qian;Xiaoning Qian;Shuiwang Ji

Learning Fair Graph Representations via Automated Data Augmentations

DOI：
发表时间：
2023
期刊：
影响因子：
0
作者：
Hongyi Ling;Zhimeng Jiang;Youzhi Luo;S. Ji;Na Zou
通讯作者：
Hongyi Ling;Zhimeng Jiang;Youzhi Luo;S. Ji;Na Zou

Group Equivariant Fourier Neural Operators for Partial Differential Equations

DOI：
10.48550/arxiv.2306.05697
发表时间：
2023-06
期刊：
影响因子：
0
作者：
Jacob Helwig;Xuan Zhang;Cong Fu;Jerry Kurtin;Stephan Wojtowytsch;Shuiwang Ji
通讯作者：
Jacob Helwig;Xuan Zhang;Cong Fu;Jerry Kurtin;Stephan Wojtowytsch;Shuiwang Ji