Graph Convolutional Network with elastic topology

Zhihao Wu, Zhaoliang Chen, Shide Du, Sujia Huang, Shiping Wang

Abstract: Highlights•Present a more flexible Laplacian embedding, which suppresses the affect of outliers.•Propose a block-based framework with learnable topology inspired by the flexible optimization.•A set-level orthogonal loss is put forward, which improves the cross-entropy loss.•The proposed method shows superiority via comprehensive experiments.