Collaborative Research: III: Medium: Graph Neural Networks for Heterophilous Data: Advancing the Theory, Models, and Applications

合作研究：III：媒介：异质数据的图神经网络：推进理论、模型和应用

• 批准号: 2212145
• 负责人: Yao Ma
• 金额: $ 40万
• 依托单位: New Jersey Institute of Technology
• 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: 2022-10-01 至 2023-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2212145&HistoricalAwards=false
• 关键词: Collaborative; Research; III; Medium; Graph

Graph neural networks (GNNs), which translate the success of deep learning to graph-structured data, have numerous applications spanning from recommendation systems and fraud detection to medicine to finance. In such applications, the extent to which similar entities connect with each other---known as homophily---is unknown and cannot be computed empirically due to limited labeled data. Though homophily is common, it is not universal; there are important real-world settings where "opposites attract", leading to heterophily (low homophily). By moving beyond a reliance on graph homophily and introducing new GNN models, this project will generalize GNNs to work effectively in a wider range of domains. It will also help rectify some negative consequences of GNNs that are tailored to homophilous graphs, including biased, unfair, or erroneous predictions when applied to heterophilous data. Focusing on robustness, fairness, and explainability will help support accountable algorithmic decision-making in the domains where GNN models are employed. In addition to research, this project will support the training of a diverse cohort of undergraduate and graduate students at the University of Michigan, the New Jersey Institute of Technology, and Michigan State University via integration of this research in advanced courses, capstone projects, and other opportunities to directly contribute to this research program.The inability of GNNs to generalize their strong performance on homophilous or assortative graphs to many heterophilous graphs has attracted significant attention, and has led to empirical demonstration of the existence of "good heterophily", where GNNs can perform well. However, there is still limited understanding about the types of heterophily that are easy or difficult to handle with GNNs, especially beyond the limited, typically-studied settings (i.e., node classification on small homogeneous graphs). This project will advance the theoretical underpinnings of the interplay between different types of heterophily and GNNs, considering properties beyond just accuracy, which are necessary for deployment. Specifically, it will contribute: (a) New Theory: It will formally characterize the heterophily-related challenges of GNNs to provide a deeper understanding into "good" and "bad" heterophily, and enhance our understanding of "good" types of heterophily, which some architectures can model effectively, but have been vastly ignored until now. (b) New Models: Based on the new theory, it will introduce new GNN designs and architectures that not only have strong performance across different levels and types of heterophily, but are also robust, fair, and transparent, which are crucial for algorithmic decision-making. (c) New Applications: The project will also go beyond the traditional tasks and heterophilous network types investigated in the literature, and will include exploration of high-impact applications along with collaborators in academia and industry.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 (GNN) 将深度学习的成功转化为图结构数据，具有从推荐系统、欺诈检测到医学、金融等众多应用。在此类应用中，相似实体彼此连接的程度（称为同质性）是未知的，并且由于标记数据有限，无法凭经验计算。尽管同质性很常见，但它并不普遍。在一些重要的现实世界环境中，“异性相吸”，导致异质性（低同质性）。通过超越对图同质性的依赖并引入新的 GNN 模型，该项目将推广 GNN，以便在更广泛的领域中有效地工作。它还将有助于纠正针对同质图定制的 GNN 的一些负面后果，包括应用于异质数据时的偏见、不公平或错误预测。关注稳健性、公平性和可解释性将有助于支持使用 GNN 模型的领域中负责任的算法决策。除了研究之外，该项目还将通过将这项研究整合到高级课程、顶点项目和其他机会中，支持对密歇根大学、新泽西理工学院和密歇根州立大学的不同本科生和研究生群体进行培训，以直接为该研究项目做出贡献。GNN 无法将其在同亲图或分类图上的强大性能推广到许多异亲图上，这引起了人们的广泛关注。 引起了人们的关注，并导致了“良好异质性”存在的实证证明，其中 GNN 可以表现良好。然而，对于 GNN 容易或难以处理的异质类型的理解仍然有限，特别是超出有限的、典型研究的设置（即小型同质图上的节点分类）。该项目将推进不同类型的异质性和 GNN 之间相互作用的理论基础，考虑部署所需的不仅仅是准确性的属性。具体来说，它将贡献：（a）新理论：它将正式描述 GNN 与异质性相关的挑战，以提供对“好”和“坏”异质性的更深入理解，并增强我们对“好”类型异质性的理解，一些架构可以有效地建模，但迄今为止一直被广泛忽视。 (b)新模型：基于新理论，将引入新的GNN设计和架构，这些设计和架构不仅在不同级别和类型的异质性上具有强大的性能，而且还具有鲁棒性、公平性和透明性，这对于算法决策至关重要。 (c) 新应用：该项目还将超越文献中研究的传统任务和异质网络类型，并将包括与学术界和工业界的合作者一起探索高影响力的应用程序。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

Are Message Passing Neural Networks Really Helpful for Knowledge Graph Completion?

• DOI: 10.18653/v1/2023.acl-long.597
• 发表时间: 2022-05
• 作者: Juanhui Li;Harry Shomer;Jiayu Ding;Yiqi Wang;Yao Ma;Neil Shah;Jiliang Tang;Dawei Yin