Graph Neural Networks (GNNs) have risen to prominence in learning representations for graph structured data. A single GNN layer typically consists of a feature transformation and a feature aggregation operation. The former normally uses feed-forward networks to transform features, while the latter aggregates the transformed features over the graph. Numerous recent works have proposed GNN models with different designs in the aggregation operation. In this work, we establish mathematically that the aggregation processes in a group of representative GNN models including GCN, GAT, PPNP, and APPNP can be regarded as (approximately) solving a graph denoising problem with a smoothness assumption. Such a unified view across GNNs not only provides a new perspective to understand a variety of aggregation operations but also enables us to develop a unified graph neural network framework UGNN. To demonstrate its promising potential, we instantiate a novel GNN model, ADA-UGNN, derived from UGNN, to handle graphs with adaptive smoothness across nodes. Comprehensive experiments show the effectiveness of ADA-UGNN.
翻译:图形结构数据(GNNs)在学习图形结构数据时已变得显眼。 单个GNN层通常包含特征转换和特征聚合操作。 前者通常使用向前网络来改造特征,而后者则汇总图上的变化特征。 许多最近的工作提出了GNN模型,在集成操作中设计不同。 在这项工作中,我们数学地确定,一组具有代表性的GNN模型(包括GCN、GAT、PPNP和APPNP)中的聚合过程可被视为( 约) 以平稳假设的方式解决图表去音问题。 在整个GNNs之间这种统一的观点不仅提供了了解各种聚合操作的新视角,而且还使我们能够开发一个统一的图形神经网络框架UGNN。 为了展示其有潜力的潜力,我们立即启用了来自UGNNN的新型GNNM模型(ADA-UGNN),以便处理各节点的适应性平稳的图表。 全面实验显示ADA-UNNNN的功效。