Results 311 to 312 of about 115,093 (312)
Some of the next articles are maybe not open access.
Probability graph complementation contrastive learning
Neural NetworksGraph Neural Network (GNN) has achieved remarkable progress in the field of graph representation learning. The most prominent characteristic, propagating features along the edges, degrades its performance in most heterophilic graphs. Certain researches make attempts to construct KNN graph to improve the graph homophily.
Wenhao Jiang, Yuebin Bai
openaire +2 more sources