22 citations · 37 across the 13 of their papers we have counts for
13 papers
When Retrieval Helps: Selective Retrieval for Single-Turn Mental-Health QA
Hyunseo Oh, Chong-Kwon Kim, Yoonhyuk Choi
Retrieval-augmented generation (RAG) can improve the specificity and grounding of large language model responses, but its effect is not uniformly beneficial in single-turn mental-h…
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…
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…
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…
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…
Better Not to Propagate: Understanding Edge Uncertainty and Over-smoothing in Signed Graph Neural Networks
Yoonhyuk Choi, Jiho Choi, Taewook Ko +1
Traditional Graph Neural Networks (GNNs) rely on network homophily, which can lead to performance degradation due to over-smoothing in many real-world heterophily scenarios. Recent…
Review-Based Hyperbolic Cross-Domain Recommendation
Yoonhyuk Choi, Jiho Choi, Taewook Ko +1
The issue of data sparsity poses a significant challenge to recommender systems. In response to this, algorithms that leverage side information such as review texts have been propo…
Finding Heterophilic Neighbors via Confidence-based Subgraph Matching for Semi-supervised Node Classification
Yoonhyuk Choi, Jiho Choi, Taewook Ko +1
Graph Neural Networks (GNNs) have proven to be powerful in many graph-based applications. However, they fail to generalize well under heterophilic setups, where neighbor nodes have…
Signed Directed Graph Contrastive Learning with Laplacian Augmentation
Taewook Ko, Yoonhyuk Choi, Chong-Kwon Kim
Graph contrastive learning has become a powerful technique for several graph mining tasks. It learns discriminative representation from different perspectives of augmented graphs.…
Improving Signed Propagation for Graph Neural Networks in Multi-Class Environments
Yoonhyuk Choi, Jiho Choi, Taewook Ko +1
Message-passing Graph Neural Networks (GNNs), which collect information from adjacent nodes achieve dismal performance on heterophilic graphs. Various schemes have been proposed to…
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)…
A Graph Convolution for Signed Directed Graphs
Taewook Ko, Chong-Kwon Kim
A signed directed graph is a graph with sign and direction information on the edges. Even though signed directed graphs are more informative than unsigned or undirected graphs, the…
Review-Based Domain Disentanglement without Duplicate Users or Contexts for Cross-Domain Recommendation
Yoonhyuk Choi, Jiho Choi, Taewook Ko +2
A cross-domain recommendation has shown promising results in solving data-sparsity and cold-start problems. Despite such progress, existing methods focus on domain-shareable inform…