MHGC: Multi-scale hard sample mining for contrastive deep graph clustering

Tao Ren, Haodong Zhang, Yifan Wang, Wei Ju, Chengwu Liu, Fanchun Meng, Siyu Yi, Xiao Luo

Abstract: Highlights•We propose a novel model called MHGC for deep graph clustering.•We use multi-scale contrastive learning to capture high-order structural contexts.•We fuse beta mixture model and hard sample mining to improve discriminative capacity.•Our model outperforms SOTA baselines through extensive experiments.