Graph Neural Networks (GNNs) have demonstrated remarkable efficacy in tackling a wide array of graph-related tasks across diverse domains. However, a significant challenge lies in their propensity to generate biased predictions, particularly with respect to sensitive node attributes such as age and gender. These biases, inherent in many machine learning models, are amplified in GNNs due to the message-passing mechanism, which allows nodes to influence each other, rendering the task of making fair predictions notably challenging. This issue is particularly pertinent in critical domains where model fairness holds paramount importance. In this paper, we propose a novel generative Fairness-Aware Subgraph Diffusion (FASD) method for unbiased GNN learning. The method initiates by strategically sampling small subgraphs from the original large input graph, and then proceeds to conduct subgraph debiasing via generative fairness-aware graph diffusion processes based on stochastic differential equations (SDEs). To effectively diffuse unfairness in the input data, we introduce additional adversary bias perturbations to the subgraphs during the forward diffusion process, and train score-based models to predict these applied perturbations, enabling them to learn the underlying dynamics of the biases present in the data. Subsequently, the trained score-based models are utilized to further debias the original subgraph samples through the reverse diffusion process. Finally, FASD induces fair node predictions on the input graph by performing standard GNN learning on the debiased subgraphs. Experimental results demonstrate the superior performance of the proposed method over state-of-the-art Fair GNN baselines across multiple benchmark datasets.
An Efficient Subgraph GNN with Provable Substructure Counting Power
Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机研究所);Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院);Beijing Institute for General Artificial Intelligence(北京通用人工智能研究院)
SpanGNN: Towards Memory-Efficient Graph Neural Networks via Spanning Subgraph Training
Beijing University of Posts and Telecommunications(北京邮电大学);Hong Kong University of Science and Technology(香港科技大学);Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
Cross-attentive Cohesive Subgraph Embedding to Mitigate Oversquashing in GNNs
Department of Computer Science, Georgia State University(佐治亚州立大学计算机科学系);Department of Data Science and Analytics, Kennesaw State University(肯尼索州立大学数据科学与分析系)
A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening
Computer Science Technion - Israel Institute of Technology(技术学院-以色列理工学院计算机科学系);Electrical & Computer Engineering Technion - Israel Institute of Technology(技术学院-以色列理工学院电气与计算机工程系);NVIDIA Research(NVIDIA研究)
Bring Your Own View: Graph Neural Networks for Link Prediction with Personalized Subgraph Selection
Texas A&M University(德州农工大学);The Hong Kong Polytechnic University(香港理工大学);University of Georgia(佐治亚大学);Rice University(莱斯大学);Samsung Electronics America(三星电子美国公司);Samsung Electronics(三星电子)
Ripple Walk Training: A Subgraph-based training framework for Large and Deep Graph Neural Network
Florida State University(佛罗里达州立大学)
图神经网络(GNN)在学习图结构数据和各种任务方面取得了出色的性能。然而,许多当前的GNN在面对大型图或使用更深层次的结构时会遇到三个常见问题:邻居爆炸,节点依赖和过度平滑。这些问题与图本身的数据结构或多层GNNs框架的设计有关,并且可能导致低训练效率和高空间复杂度。为了解决这些问题,本文提出了一个通用的基于子图的训练框架,即Ripple Walk Training(RWT),用于深度和大型图神经网络。RWT从全图中采样子图以构成小批量,并且基于小批量梯度更新全GNN。我们分析了高质量的子图,训练GNN的理论方法。Ripple Walk Sampler是一种新的采样方法,它对这些高质量的子图进行采样以构成小批量,该方法同时考虑了图结构数据的随机性和连通性。在不同大小的图上进行的大量实验证明了RWT在训练各种GNN(GCN和GAT)时的有效性和效率。
Efficient Higher-order Subgraph Attribution via Message Passing
BIFOLD -- Berlin Institute for the Foundations of Learning(柏林学习与数据基础研究院);Department of Artificial Intelligence, Korea University, Seoul 136-713, Korea(韩国大学人工智能系);RIKEN Center for AIP, Japan(日本AIP研究中心)
GraphEdge: Dynamic Graph Partition and Task Scheduling for GNNs Computing in Edge Network
Guangxi Key Laboratory of Multimedia Communications and Network Technology(广西多媒体通信与网络技术重点实验室);School of Computer, Electronics and Information, Guangxi University(广西大学计算机、电子与信息学院);School of Computer Science and Engineering, South China University of Technology(华南理工大学计算机科学与工程学院);Pazhou Laboratory(琶洲实验室);College of Cyber Security, Jinan University(暨南大学网络安全学院);Department of Information Systems, University of Maryland, Baltimore County (UMBC)(马里兰大学巴尔的摩县信息学院)
Iterative Graph Neural Network Enhancement via Frequent Subgraph Mining of Explanations
University of Illinois at Chicago(伊利诺伊大学芝加哥分校);University of Bonn(波恩大学);Fraunhofer IAIS(弗劳恩霍夫智能分析与信息系统研究所);Lamarr Institute for Machine Learning and Artificial Intelligence(拉马尔机器学习与人工智能研究所);HUN-REN-SZTE Research Group on AI(HUN-REN-塞格德大学人工智能研究组)
本文研究了图神经网络(GNNs)的忠实解释。首先,我们提供了一个新的和一般的方法来正式表征GNN的解释的忠实性。它适用于现有的解释方法,包括特征属性和子图解释。其次,我们的分析和实证结果表明,特征属性的方法不能捕捉边缘特征的非线性效应,而现有的子图解释方法是不忠实的。第三,我们介绍了\emph{k-hop Explanation with a Convolutional Core}(KEC),一种新的解释方法,可证明最大限度地忠实于原来的GNN利用信息的图结构在其邻接矩阵和它的\emph{k-th}权力。最后,我们对使用GNN进行分类和异常检测任务的合成和真实数据集的实证结果证明了我们方法的有效性。