118 citations · 537 across the 31 of their papers we have counts for
15 papers · 1 filter
Deep Multimodal Fusion by Channel Exchanging
Yikai Wang, Wenbing Huang, Fuchun Sun +3
Deep multimodal fusion by using multiple sources of data for classification or regression has exhibited a clear advantage over the unimodal counterpart on various applications. Yet…
Hierarchical Graph Capsule Network
Jinyu Yang, Peilin Zhao, Yu Rong +4
Graph Neural Networks (GNNs) draw their strength from explicitly modeling the topological information of structured data. However, existing GNNs suffer from limited capability in c…
Dirichlet Graph Variational Autoencoder
Jia Li, Tomasyu Yu, Jiajin Li +5
Graph Neural Networks (GNNs) and Variational Autoencoders (VAEs) have been widely used in modeling and generating graphs with latent factors. However, there is no clear explanation…
On Self-Distilling Graph Neural Network
Yuzhao Chen, Yatao Bian, Xi Xiao +3
Recently, the teacher-student knowledge distillation framework has demonstrated its potential in training Graph Neural Networks (GNNs). However, due to the difficulty of training o…
Graph Information Bottleneck for Subgraph Recognition
Junchi Yu, Tingyang Xu, Yu Rong +3
Given the input graph and its label/property, several key problems of graph learning, such as finding interpretable subgraphs, graph denoising and graph compression, can be attribu…
Tackling Over-Smoothing for General Graph Convolutional Networks
Wenbing Huang, Yu Rong, Tingyang Xu +2
Increasing the depth of GCN, which is expected to permit more expressivity, is shown to incur performance detriment especially on node classification. The main cause of this lies i…