← Search

Cheonwoo Lee

2 accepted papers

2025

Aggregation Buffer: Revisiting DropEdge with a New Parameter Block

ICML 2025poster

We revisit DropEdge, a data augmentation technique for GNNs which randomly removes edges to expose diverse graph structures during training. While being a promising approach to effectively reduce overfitting on specific connections in the graph, we observe that its potential performance gain in supe…