13 citations · 52 across the 22 of their papers we have counts for
4 papers · 1 filter
Non-equispaced Fourier Neural Solvers for PDEs
Haitao Lin, Lirong Wu, Yongjie Xu +4
Solving partial differential equations is difficult. Recently proposed neural resolution-invariant models, despite their effectiveness and efficiency, usually require equispaced sp…
Are Gradients on Graph Structure Reliable in Gray-box Attacks?
Zihan Liu, Yun Luo, Lirong Wu +3
Graph edge perturbations are dedicated to damaging the prediction of graph neural networks by modifying the graph structure. Previous gray-box attackers employ gradients from the s…
Discovering the Representation Bottleneck of Graph Neural Networks
Fang Wu, Siyuan Li, Stan Z. Li
Graph neural networks (GNNs) rely mainly on the message-passing paradigm to propagate node features and build interactions, and different graph learning problems require different…
Harnessing Hard Mixed Samples with Decoupled Regularizer
Zicheng Liu, Siyuan Li, Ge Wang +3
Mixup is an efficient data augmentation approach that improves the generalization of neural networks by smoothing the decision boundary with mixed data. Recently, dynamic mixup met…