Search Results for author:
Found 5 papers, 2 papers with code
Taxonomic Class Incremental Learning
In this work, we propose the Taxonomic Class Incremental Learning (TCIL) problem.
Learnable Hypergraph Laplacian for Hypergraph Learning
Hypergraph Convolutional Neural Networks (HGCNNs) have demonstrated their potential in modeling high-order relations preserved in graph-structured data.
Learnable Hypergraph Laplacian for Hypergraph Learning
HyperGraph Convolutional Neural Networks (HGCNNs) have demonstrated their potential in modeling high-order relations preserved in graph structured data.
Diversified Multiscale Graph Learning with Graph Self-Correction
Though the multiscale graph learning techniques have enabled advanced feature extraction frameworks, the classic ensemble strategy may show inferior performance while encountering the high homogeneity of the learnt representation, which is caused by the nature of existing graph pooling methods.
On Self-Distilling Graph Neural Network
Furthermore, the inefficient training process of teacher-student knowledge distillation also impedes its applications in GNN models.
