2020/09/24 by Hongwei Zhang, Zhang, Hongwei, Tijin Yan +7
Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Caching and Content Delivery #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Recommender Systems and Techniques
paper · pdf · doi:10.48550/arxiv.2009.11469
openalex publication_date 2020/09/24 · openalex created_date 2020/10/01 · openalex updated_date 2026/07/28
Graph convolutional networks (GCNs) have achieved promising performance on various graph-based tasks. However they suffer from over-smoothing when stacking more layers. In this paper, we present a quantitative study on this observation and develop novel insights towards the deeper GCN. First, we interpret the current graph convolutional operations from an optimization perspective and argue that over-smoothing is mainly caused by the naive first-order approximation of the solution to the optimization problem. Subsequently, we introduce two metrics to measure the over-smoothing on node-level tasks. Specifically, we calculate the fraction of the pairwise distance between connected and disconnected nodes to the overall distance respectively. Based on our theoretical and empirical analysis, we establish a universal theoretical framework of GCN from an optimization perspective and derive a novel convolutional kernel named GCN+ which has lower parameter amount while relieving the over-smoothing inherently. Extensive experiments on real-world datasets demonstrate the superior performance of GCN+ over state-of-the-art baseline methods on the node classification tasks.