activity
20192022
most citedMatrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning

34 citations · 54 across the 7 of their papers we have counts for

collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2022★ 1 cited

Deep Manifold Learning with Graph Mining

Xuelong Li, Ziheng Jiao, Hongyuan Zhang +1

Admittedly, Graph Convolution Network (GCN) has achieved excellent results on graph datasets such as social networks, citation networks, etc. However, softmax used as the decision…

cs.LG2022★ 34 cited

Matrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning

Xuelong Li, Hongyuan Zhang, Rui Zhang

The existing matrix completion methods focus on optimizing the relaxation of rank function such as nuclear norm, Schatten-p norm, etc. They usually need many iterations to converge…

cs.LG2021

AnchorGAE: General Data Clustering via Bipartite Graph Convolution

Hongyuan Zhang, Jiankun Shi, Rui Zhang +1

Since the representative capacity of graph-based clustering methods is usually limited by the graph constructed on the original features, it is attractive to find whether graph neu…

cs.LG2021

Non-Gradient Manifold Neural Network

Rui Zhang, Ziheng Jiao, Hongyuan Zhang +1

Deep neural network (DNN) generally takes thousands of iterations to optimize via gradient descent and thus has a slow convergence. In addition, softmax, as a decision layer, may i…

cs.LG2021

WGCN: Graph Convolutional Networks with Weighted Structural Features

Yunxiang Zhao, Jianzhong Qi, Qingwei Liu +1

Graph structural information such as topologies or connectivities provides valuable guidance for graph convolutional networks (GCNs) to learn nodes' representations. Existing GCN m…

cs.LG2021

LGD-GCN: Local and Global Disentangled Graph Convolutional Networks

Jingwei Guo, Kaizhu Huang, Xinping Yi +1

Disentangled Graph Convolutional Network (DisenGCN) is an encouraging framework to disentangle the latent factors arising in a real-world graph. However, it relies on disentangling…