activity
20172021
most citedStructural Deep Clustering Network

519 citations · 1.3k across the 18 of their papers we have counts for

collaborators
Showing cs.LGShow all

12 papers · 1 filter

cs.LG202127 cited

Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning

Xiao Wang, Nian Liu, Hui Han +1

Heterogeneous graph neural networks (HGNNs) as an emerging technique have shown superior capacity of dealing with heterogeneous information network (HIN). However, most HGNNs follo…

cs.LG20211 cited

Lorentzian Graph Convolutional Networks

Yiding Zhang, Xiao Wang, Chuan Shi +2

Graph convolutional networks (GCNs) have received considerable research attention recently. Most GCNs learn the node representations in Euclidean geometry, but that could have a hi…

cs.LG20218 cited

Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework

Cheng Yang, Jiawei Liu, Chuan Shi

Semi-supervised learning on graphs is an important problem in the machine learning area. In recent years, state-of-the-art classification methods based on graph neural networks (GN…

cs.LG202128 cited

Interpreting and Unifying Graph Neural Networks with An Optimization Framework

Meiqi Zhu, Xiao Wang, Chuan Shi +2

Graph Neural Networks (GNNs) have received considerable attention on graph-structured data learning for a wide variety of tasks. The well-designed propagation mechanism which has b…

cs.LG202122 cited

Beyond Low-frequency Information in Graph Convolutional Networks

Deyu Bo, Xiao Wang, Chuan Shi +1

Graph neural networks (GNNs) have been proven to be effective in various network-related tasks. Most existing GNNs usually exploit the low-frequency signals of node features, which…

cs.LG2020492 cited

AM-GCN: Adaptive Multi-channel Graph Convolutional Networks

Xiao Wang, Meiqi Zhu, Deyu Bo +3

Graph Convolutional Networks (GCNs) have gained great popularity in tackling various analytics tasks on graph and network data. However, some recent studies raise concerns about wh…