8 papers
Gauge-Equivariant Graph Networks via Self-Interference Cancellation
Yoonhyuk Choi, Jiho Choi, Jiwoo Kang
Graph Neural Networks (GNNs) excel on homophilous graphs but often fail under heterophily due to self-reinforcing and phase-inconsistent signals. We propose a \textbf{G}auge-\textb…
Sparse Bayesian Message Passing under Structural Uncertainty
Yoonhyuk Choi, Jiho Choi, Chanran Kim +5
Semi-supervised learning on real-world graphs is frequently challenged by heterophily, where the observed graph is unreliable or label-disassortative. Many existing graph neural ne…
Sheaf Graph Neural Networks via PAC-Bayes Spectral Optimization
Yoonhyuk Choi, Jiho Choi, Chong-Kwon Kim
Over-smoothing in Graph Neural Networks (GNNs) causes collapse in distinct node features, particularly on heterophilic graphs where adjacent nodes often have dissimilar labels. Alt…
Adaptive Branch Specialization in Spectral-Spatial Graph Neural Networks for Certified Robustness
Yoonhyuk Choi, Jiho Choi, Chong-Kwon Kim
Recent Graph Neural Networks (GNNs) combine spectral-spatial architectures for enhanced representation learning. However, limited attention has been paid to certified robustness, p…
Hierarchical Uncertainty-Aware Graph Neural Network
Yoonhyuk Choi, Jiho Choi, Taewook Ko +1
Recent research on graph neural networks (GNNs) has explored mechanisms for capturing local uncertainty and exploiting graph hierarchies to mitigate data sparsity and leverage stru…
Mitigating Overfitting in Graph Neural Networks via Feature and Hyperplane Perturbation
Yoonhyuk Choi, Jiho Choi, Taewook Ko +1
Graph neural networks (GNNs) are commonly used in semi-supervised settings. Previous research has primarily focused on finding appropriate graph filters (e.g. aggregation methods)…