activity
20212025
most citedClassification of Edge-dependent Labels of Nodes in Hypergraphs

17 citations · 35 across the 18 of their papers we have counts for

collaborators

18 papers

cs.SI2025

Identifying Group Anchors in Real-World Group Interactions Under Label Scarcity

Fanchen Bu, Geon Lee, Minyoung Choe +1

Group interactions occur in various real-world contexts, e.g., co-authorship, email communication, and online Q&A. In each group, there is often a particularly significant member,…

cs.DB2025

MARIOH: Multiplicity-Aware Hypergraph Reconstruction

Kyuhan Lee, Geon Lee, Kijung Shin

Hypergraphs offer a powerful framework for modeling higher-order interactions that traditional pairwise graphs cannot fully capture. However, practical constraints often lead to th…

cs.IR20255 cited

KGMEL: Knowledge Graph-Enhanced Multimodal Entity Linking

Juyeon Kim, Geon Lee, Taeuk Kim +1

Entity linking (EL) aligns textual mentions with their corresponding entities in a knowledge base, facilitating various applications such as semantic search and question answering.…

cs.LG2025

Simple yet Effective Node Property Prediction on Edge Streams under Distribution Shifts

Jongha Lee, Taehyung Kwon, Heechan Moon +1

The problem of predicting node properties (e.g., node classes) in graphs has received significant attention due to its broad range of applications. Graphs from real-world datasets…

cs.LG20246 cited

Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy

Sunwoo Kim, Soo Yong Lee, Fanchen Bu +4

Graph autoencoders (Graph-AEs) learn representations of given graphs by aiming to accurately reconstruct them. A notable application of Graph-AEs is graph-level anomaly detection (…

cs.LG20244 cited

HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs

Sunwoo Kim, Shinhwan Kang, Fanchen Bu +3

Hypergraphs are marked by complex topology, expressing higher-order interactions among multiple nodes with hyperedges, and better capturing the topology is essential for effective…