Aggregation Buffer: Revisiting DropEdge with a New Parameter Block
This work provides a unifying solution to enhance GNN robustness and address structural disparities in graph learning, though it is incremental as it builds on existing DropEdge methodology.
The authors identified that DropEdge, a graph data augmentation technique, has limited performance gains due to fundamental limitations in GNN architectures, and proposed Aggregation Buffer, a parameter block that improves robustness and addresses issues like degree bias, showing consistent improvements on multiple datasets.
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 supervised learning tasks is significantly limited. To understand why, we provide a theoretical analysis showing that the limited performance of DropEdge comes from the fundamental limitation that exists in many GNN architectures. Based on this analysis, we propose Aggregation Buffer, a parameter block specifically designed to improve the robustness of GNNs by addressing the limitation of DropEdge. Our method is compatible with any GNN model, and shows consistent performance improvements on multiple datasets. Moreover, our method effectively addresses well-known problems such as degree bias or structural disparity as a unifying solution. Code and datasets are available at https://github.com/dooho00/agg-buffer.