GraphAlign: Pretraining One Graph Neural Network on Multiple Graphs via Feature Alignment
This addresses the challenge of training graph neural networks across varied graph domains, which is incremental as it builds upon existing graph SSL frameworks.
The paper tackled the problem of feature discrepancy across different graphs in graph self-supervised learning by proposing GraphAlign, a method that aligns feature distributions to pretrain a single graph neural network on multiple graphs, resulting in performance superiority on both in-domain and out-of-domain graphs.
Graph self-supervised learning (SSL) holds considerable promise for mining and learning with graph-structured data. Yet, a significant challenge in graph SSL lies in the feature discrepancy among graphs across different domains. In this work, we aim to pretrain one graph neural network (GNN) on a varied collection of graphs endowed with rich node features and subsequently apply the pretrained GNN to unseen graphs. We present a general GraphAlign method that can be seamlessly integrated into the existing graph SSL framework. To align feature distributions across disparate graphs, GraphAlign designs alignment strategies of feature encoding, normalization, alongside a mixture-of-feature-expert module. Extensive experiments show that GraphAlign empowers existing graph SSL frameworks to pretrain a unified and powerful GNN across multiple graphs, showcasing performance superiority on both in-domain and out-of-domain graphs.