activity
20172026
most citedLTE4G: Long-Tail Experts for Graph Neural Networks

41 citations · 227 across the 27 of their papers we have counts for

collaborators
Showing cs.LGShow all

20 papers · 1 filter

cs.LG2026

DefaultGNN: A Dual-Perspective GNN Framework for Predicting Corporate Default from Buyer-Seller Transaction Networks

Junghoon Kim, Hyunsung Kim, Seungyoon Choi +4

Corporate default prediction is a core problem in financial risk management, yet traditional credit models rely heavily on financial statements that are often sparse or unavailable…

cs.LG2023★ 12 cited

Class Label-aware Graph Anomaly Detection

Junghoon Kim, Yeonjun In, Kanghoon Yoon +2

Unsupervised GAD methods assume the lack of anomaly labels, i.e., whether a node is anomalous or not. One common observation we made from previous unsupervised methods is that they…

cs.LG2023★ 5 cited

S-Mixup: Structural Mixup for Graph Neural Networks

Junghurn Kim, Sukwon Yun, Chanyoung Park

Existing studies for applying the mixup technique on graphs mainly focus on graph classification tasks, while the research in node classification is still under-explored. In this p…

cs.LG2023★ 1 cited

Similarity Preserving Adversarial Graph Contrastive Learning

Yeonjun In, Kanghoon Yoon, Chanyoung Park

Recent works demonstrate that GNN models are vulnerable to adversarial attacks, which refer to imperceptible perturbation on the graph structure and node features. Among various GN…

cs.LG2023★ 10 cited

Task-Equivariant Graph Few-shot Learning

Sungwon Kim, Junseok Lee, Namkyeong Lee +3

Although Graph Neural Networks (GNNs) have been successful in node classification tasks, their performance heavily relies on the availability of a sufficient number of labeled node…

cs.LG2023

Unsupervised Episode Generation for Graph Meta-learning

Jihyeong Jung, Sangwoo Seo, Sungwon Kim +1

We propose Unsupervised Episode Generation method called Neighbors as Queries (NaQ) to solve the Few-Shot Node-Classification (FSNC) task by unsupervised Graph Meta-learning. Doing…