An Efficient Prototype-Based Clustering Approach for Edge Pruning in Graph Neural Networks to Battle Over-Smoothing
Huang Y, Lu W, Yang Y. An Efficient Prototype-Based Clustering Approach for Edge Pruning in Graph Neural Networks to Battle Over-Smoothing. 2024, 4201-4209. DOI: 10.24963/ijcai.2024/464.Peer-Reviewed Original ResearchGraph neural networksOver-smoothingNeural networkIssue of over-smoothingIntra-class edgesEmbeddings of nodesGroup of nodesGNNs’ performanceNode representationsSupervision signalsClass labelsPreserving smoothingInter-classEfficient clusteringEdge pruningGraph structureDiverse graphsClustering approachTopology augmentationGraphNodesEnhanced accuracyNetworkAccuracyScalability