LGMay 30

RADE: Random Add-Drop Edge as a Regularizer

arXiv:2606.0075727.9h-index: 14
Predicted impact top 75% in LG · last 90 daysOriginality Incremental advance
AI Analysis

Provides a unified stochastic augmentation method for GNNs that addresses both overfitting and over-squashing, a known bottleneck in graph representation learning.

RADE jointly drops and adds edges in GNNs to regularize against overfitting and mitigate over-squashing, achieving strong performance on node and graph classification benchmarks with a hyperparameter-free adaptive rate algorithm.

Graph Neural Networks (GNNs) suffer from overfitting and over-squashing of long-range information. Stochastic graph augmentations (e.g., edge deletion) regularize training against overfitting but can introduce train-inference misalignment and do not improve over-squashing. In contrast, rewiring methods improve connectivity to mitigate over-squashing, but are not designed to regularize training. We propose Random Add-Drop Edge (RADE), a stochastic graph augmentation method that jointly drops and adds edges to address both overfitting and over-squashing simultaneously. RADE is provably designed to align training and inference so that random augmentations regularize training without distribution shift, while supporting long-range communication at inference. We further propose and study a mini-batch gradient-norm balancing algorithm that adapts deletion and addition rates during training, rendering RADE hyperparameter-free in practice. Experiments on node- and graph-classification benchmarks show that RADE is a strong regularizer and mitigates over-squashing. Ablations support the roles of train-inference alignment, adaptive rate selection, and the complementary effects of random edge deletion and edge addition.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes