EAGER: Weakly Supervised Graph Neural Networks

EAGER：弱监督图神经网络

• 批准号: 2137468
• 负责人: Jingrui He
• 金额: $ 14.99万
• 依托单位: University of Illinois at Urbana-Champaign
• 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: 2021-10-01 至 2023-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2137468&HistoricalAwards=false
• 关键词: EAGER; Weakly; Supervised; Graph; Neural

Graph Neural Networks have proven to be a powerful tool for harnessing graph data, which is widely used for representing rich relational information in multiple areas. However, the performance of graph neural networks largely depends on the amount of labeled data, and thus can be significantly affected by the label scarcity caused by the expensive and time-consuming annotation process, which is common among many high-impact applications, such as fraud detection, agriculture, cancer diagnosis. This project focuses on building high-performing graph neural networks in the presence of label scarcity. In particular, the developed techniques advance state-of-the-art by systematically leveraging weak supervision in the form of relevant source graphs and access to a labeling oracle with a limited budget. This project generates a suite of new models, algorithms and theories for constructing high-performing graph neural networks with weak supervision, and for understanding the benefits of weak supervision from a theoretical perspective. It advances state-of-the-practice for graph neural networks by significantly reducing the need for large amount of labeled data. This project involves students at various levels, especially those from under-represented groups. The research outcomes from this project will be disseminated at relevant conferences and journals in computer science.This project consists of two complementary research thrusts, focusing on the pre-training stage and the fine-tuning stage of the model construction process for graph neural networks respectively. For the pre-training stage, given the rich information from relevant source graphs, this project develops techniques to leverage such information via cross-graph domain adaptation, in order to obtain effective representation of the target graph at various granularities; for the fine-tuning stage, given a limited budget for querying an oracle, this project develops techniques to select the most informative nodes/edges/subgraphs based on the training dynamics of graph neural networks, such that this additional label information can maximally improve the model performance. Furthermore, this project establishes new theoretical results regarding the benefits of weak supervision, such as the impact of source graphs on the model generalization performance and the reduction of the sample complexity due to active learning with graph neural networks.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.

图神经网络已被证明是利用图数据的强大工具，图数据被广泛用于表示多个领域中丰富的关系信息。然而，图神经网络的性能在很大程度上取决于标记数据的数量，因此可能会受到昂贵且耗时的注释过程导致的标签稀缺性的显著影响，这在许多高影响力的应用中很常见，例如欺诈检测，农业，癌症诊断。该项目的重点是在标签稀缺的情况下构建高性能的图神经网络。特别是，所开发的技术通过系统地利用相关源图形式的弱监督和以有限预算访问标记Oracle来推进最先进的技术。该项目产生了一套新的模型，算法和理论，用于构建具有弱监督的高性能图神经网络，并从理论角度理解弱监督的好处。它通过显着减少对大量标记数据的需求来推进图神经网络的实践状态。该项目涉及各级学生，特别是代表性不足群体的学生。本项目的研究成果将在计算机科学的相关会议和期刊上发布。本项目包括两个互补的研究方向，分别侧重于图神经网络模型构建过程的预训练阶段和微调阶段。对于预训练阶段，考虑到来自相关源图的丰富信息，该项目开发了通过跨图域适应来利用这些信息的技术，以便在各种粒度上获得目标图的有效表示;对于微调阶段，给定用于查询Oracle的有限预算，该项目开发了基于图神经网络的训练动态来选择信息量最大的节点/边/子图的技术，使得这些额外的标签信息可以最大限度地提高模型性能。此外，该项目还建立了关于弱监督的好处的新理论成果，例如源图对模型泛化性能的影响，以及通过图神经网络的主动学习降低样本复杂性。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而被认为值得支持。

项目成果

Distribution-Informed Neural Networks for Domain Adaptation Regression

用于域适应回归的分布通知神经网络

• 发表时间: 2023
• 期刊: NeurIPS
• 作者: Wu, Jun;He, Jingrui;Wang, Sheng;Guan, Kaiyu;Ainsworth, Elizabeth A.
• 通讯作者: Ainsworth, Elizabeth A.

Contrastive Learning with Complex Heterogeneity

• DOI: 10.1145/3534678.3539311
• 发表时间: 2021-05
• 期刊: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
• 作者: Lecheng Zheng;Jinjun Xiong;Yada Zhu;Jingrui He

Optimizing the Collaboration Structure in Cross-Silo Federated Learning

• DOI: 10.48550/arxiv.2306.06508
• 发表时间: 2023-06
• 期刊: ArXiv
• 作者: Wenxuan Bao;Haohan Wang;Jun Wu;Jingrui He

Robust Basket Recommendation via Noise-tolerated Graph Contrastive Learning

• DOI: 10.1145/3583780.3615039
• 发表时间: 2023-10
• 期刊: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management
• 作者: Xinrui He;Tianxin Wei;Jingrui He

Comprehensive Fair Meta-learned Recommender System

• DOI: 10.1145/3534678.3539269
• 发表时间: 2022-06
• 期刊: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
• 作者: Tianxin Wei;Jingrui He