GNNs Also Deserve Editing, and They Need It More Than Once (SEED-GNN)
This paper aims to reproduce the findings of "Editable Graph Neural Network for Node Classifications." The authors investigate correcting errors in Graph Neural Network (GNN) models, noting GNNs' editing sensitivity due to neighborhood aggregation, which corrupts the model's generalizability. They propose SEED-GNN, a solution using overfit-prevention techniques, to enable practically scalable GNN editing. (https://openreview.net/forum?id=rIc9adYbH2)
Launching this artifact will open it within Chameleon’s shared Jupyter experiment environment, which is accessible to all Chameleon users with an active allocation.
Download ArchiveDownload an archive containing the files of this artifact.
Download with git
Clone the git repository for this artifact, and checkout the version's commit
git clone https://github.com/malifalhakim/gnn_editing
# cd into the created directory
git checkout 6a33080211fb760e5ea3faa1a504c11762c59ebdSubmit feedback through GitHub issues