III: Small: Comprehensive Methods to Learn to Augment Graph Data

III：小：学习增强图数据的综合方法

• 批准号: 2146761
• 负责人: Meng Jiang
• 金额: $ 50万
• 依托单位: University of Notre Dame
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-03-01 至 2025-02-28
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2146761&HistoricalAwards=false
• 关键词: III; Small; Comprehensive; Methods; Learn

Machine learning algorithms learn from data. The quality and quantity of training data has as much to do with the success of machine learning projects as the algorithms themselves. Data augmentation methods aim at eliciting information that is not readily available in the training data, but that is needed to improve the performance of the learning systems. Data augmentation has been successfully used in image classification: from adhoc augmentation, such as cropping, flipping, rotation and 'learning ­to ­augment' methods. This work focuses on data augmentation for Graph Machine Learning (GML). GML methods such as graph neural networks (GNNs) play an important role in studying many types of graphs of significant societal importance, including social networks, molecular networks, and knowledge graphs. While augmentation methods have been applied to GML before, existing techniques are applied in an adhoc manner and yield sub-optimal results. This project will study principled methods for building computational graphs, augmenting raw graph data, aiming at improving the performance of graph learning methods.The technical aims of the project are divided into three thrusts. The first thrust develops novel graph machine learning techniques to augment the graph data by counterfactual inference on the effect of edges as treatment variables. The second thrust develops novel graph machine learning techniques to augment the graph by forecasting if sequential, temporal, or dynamic patterns exist in the data. The third thrust develops novel graph machine learning techniques to augment the graph by pseudo labeling and disconnecting the nodes in very different communities or clusters. This project will deliver novel methods to augment graph data integrating with theories and methods from a variety of research fields, such as statistical causal analysis, sequence modeling and prediction, and graph mining algorithms. It will advance the technologies of graph machine learning and expand the scope of data augmentation for deep learning.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.

机器学习算法从数据中学习，训练数据的质量和数量与机器学习项目的成功密切相关，就像数据增强方法旨在获取训练数据中不易获得的信息一样。数据增强已成功应用于图像分类：裁剪、翻转、旋转和“学习增强”方法等。这项工作重点关注图机器学习的数据增强。 （GML）。图神经网络 (GNN) 等方法在研究具有重要社会重要性的多种类型的图（包括社交网络、分子网络和知识图）方面发挥着重要作用，虽然增强方法之前已应用于 GML，但现有技术也应用于 GML。该项目将研究构建计算图、增强原始图数据的原则方法，旨在提高图学习方法的性能。该项目的技术目标分为三个主旨。推力开发新颖的图表机器学习技术通过对边缘作为处理变量的影响进行反事实推理来增强图形数据。第二个推动力开发了新颖的图形机器学习技术，通过预测数据中是否存在顺序、时间或动态模式来增强图形。新颖的图形机器学习技术通过伪标记和断开不同社区或集群中的节点来增强图形该项目将提供新颖的方法来增强图形数据，整合来自各种研究领域的理论和方法，例如统计因果分析，序列建模和预测，以及它将推进图机器学习技术并扩大深度学习的数据增强范围。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力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

Learning from Counterfactual Links for Link Prediction

从反事实链接中学习以进行链接预测

• 发表时间: 2022-07
• 期刊: ICML
• 作者: Zhao, Tong;Liu, Gang;Wang, Daheng;Yu, Wenhao;Jiang, Meng
• 通讯作者: Jiang, Meng

Graph Rationalization with Environment-based Augmentations

通过基于环境的增强进行图形合理化

• DOI: 10.1145/3534678.3539347
• 发表时间: 2022-08
• 期刊: Proceedings of the ACM SIGKDD Conference on Knowledge Discovery & Data Mining
• 作者: Liu, Gang;Zhao, Tong;Xu, Jiaxin;Luo, Tengfei;Jiang, Meng
• 通讯作者: Jiang, Meng

AutoGDA: Automated Graph Data Augmentation for Node Classification

AutoGDA：用于节点分类的自动图形数据增强

• DOI: 10.1145/3583780.3615035
• 发表时间: 2024-09-14
• 期刊: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management
• 作者: Tong Zhao;Xianfeng Tang;Danqing Zhang;Haoming Jiang;Nikhil S. Rao;Yiwei Song;Pallav Agrawal;Karthik Subbian;Bing Yin;Meng Jiang
• 通讯作者: Meng Jiang

Data-Centric Learning from Unlabeled Graphs with Diffusion Model

使用扩散模型从未标记图进行以数据为中心的学习

• 发表时间: 2023-12
• 期刊: NeurIPS
• 作者: Liu, Gang;Inae, Eric;Zhao, Tong;Xu, Jiaxin;Luo, Tengfei;Jiang, Meng
• 通讯作者: Jiang, Meng

Leveraging low-fidelity data to improve machine learning of sparse high-fidelity thermal conductivity data via transfer learning

利用低保真数据通过迁移学习改进稀疏高保真热导率数据的机器学习

• DOI: 10.1016/j.mtphys.2022.100868
• 发表时间: 2022-11
• 期刊: Materials Today Physics
• 影响因子: 11.5
• 作者: Liu, Z.;Jiang, M.;Luo, T.
• 通讯作者: Luo, T.