Robust Graph Clustering Network for Multiple Missing Data
RGCN introduces a view-decoupled dual-branch imputation to mitigate interference and enable mutual enhancement in recovering missing data, and employs a multi-hyperspherical mixture prior to enhance intra-cluster compactness and inter-cluster separability on a directional latent manifold.
Ke-Yuan Qiu, Ren-Da Han, Zhen Tang et al.
· 0 citations