Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 2 of 2 for “"GNN architectures (GCN"”.
-
Improved and domain specific model soups
… and efficiency of Graph Neural Networks (GNNs). Traditional ensemble methods, while accurate, incur significant computational and memory costs, limiting scalability. We propose two novel souping algorithms: Learned Souping (LS), which employs gradient descent to optimize weight …
-
Edge co-occurrence regularization for node classification
… on connected nodes, is then used to regularize GNN training without further updates. We evaluate this approach across multiple homophilic datasets (Cora, CiteSeer, PubMed, ogbn-arxiv) and heterophilic benchmarks (Chameleon, Squirrel, Actor, Roman-Empire) using three GNN architectures: GCN, …