Revisiting Graph Convolutional Network on Semi-Supervised Node Classification from an Optimization Perspective
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.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationNode ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Graph Convolutional Network For Semi-supervised Node Classification With Subgraph Sketching
In this paper, we propose the Graph-Learning-Dual Graph Convolutional Neural Network called GLDGCN based on the classic Graph Convolutional Neural Network(GCN) by introducing dual convolutional layer and graph learning l…
ClassificationClusteringGraph LearningNode ClassificationGraph Convolutional Networks using Heat Kernel for Semi-supervised Learning
Graph convolutional networks gain remarkable success in semi-supervised learning on graph structured data. The key to graph-based semisupervised learning is capturing the smoothness of labels or features over nodes exert…
MGCN: Semi-supervised Classification in Multi-layer Graphs with Graph Convolutional Networks
Graph embedding is an important approach for graph analysis tasks such as node classification and link prediction. The goal of graph embedding is to find a low dimensional representation of graph nodes that preserves the…
General ClassificationGraph EmbeddingLink PredictionNetwork Embedding+1Determinate Node Selection for Semi-supervised Classification Oriented Graph Convolutional Networks
Graph Convolutional Networks (GCNs) have been proved successful in the field of semi-supervised node classification by extracting structural information from graph data. However, the random selection of labeled nodes use…
Graph Neural NetworkNode ClassificationAnisotropic Graph Convolutional Network for Semi-supervised Learning
Graph convolutional networks learn effective node embeddings that have proven to be useful in achieving high-accuracy prediction results in semi-supervised learning tasks, such as node classification. However, these netw…
ClassificationGeneral ClassificationNode Classification