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"”.

  1. 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 …

    iastate Repository record for Improved and domain specific model soups (opens in a new tab)

  2. 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, …

    njit Repository record for Edge co-occurrence regularization for node classification (opens in a new tab)