Despite much research, Graph Neural Networks (GNNs) still do not display the favorable scaling properties of other deep neural networks such as Convolutional Neural Networks and Transformers. Previous work has identified issues such as oversmoothing of the latent representation and have suggested solutions such as skip connections and sophisticated normalization schemes. Here, we propose a different approach that is based on a stratification of the graph nodes. We provide motivation that the nodes in a graph can be stratified into those with a low degree and those with a high degree and that the two groups are likely to behave differently. Based on this motivation, we modify the Graph Neural Network (GNN) architecture so that the weight matrices are learned, separately, for the nodes in each group. This simple-to-implement modification seems to improve performance across datasets and GNN methods. To verify that this increase in performance is not only due to the added capacity, we also perform the same modification for random splits of the nodes, which does not lead to any improvement.
Not All Nodes Are Created Equal: Homophily-Aware Stratification for Stable GNN Evaluation
Universität Bayreuth(拜罗伊特大学);FAU Erlangen-Nürnberg(埃尔朗根-纽伦堡大学);Ludwig-Maximilians-Universität München(慕尼黑大学);Munich Center for Machine Learning(慕尼黑机器学习中心)
GraphBEAT: Graph-based Bucketized Event Aggregation Over Time for Early Risk Stratification of Gastrointestinal Cancers
Mayo Clinic(梅奥诊所);Kern Center for the Science of Health Care Delivery(克恩医疗保健科学中心);Department of Artificial Intelligence and Informatics, Mayo Clinic(梅奥诊所人工智能与信息学系)
Mitigating Degree Bias in Graph Representation Learning with Learnable Structural Augmentation and Structural Self-Attention
Department of Artificial Intelligence, The Catholic University of Korea(人工智能系,韩国天主大学);Data Assimilation Group, Korea Institute of Atmospheric Prediction Systems (KIAPS)(数据同化组,韩国大气预测研究所)
L1-regularized neural ranking for risk stratification and its application to prediction of time to distant metastasis in luminal node negative chemotherapy naïve breast cancer patients