Jaeseung Heo

According to our database, Jaeseung Heo authored at least 7 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Transductive Generalization via Optimal Transport and Its Application to Graph Node Classification.

MoonJeong Park, Seungbeom Lee, Kyungmin Kim, Jaeseung Heo, Seunghyuk Cho, Shouheng Li, Sangdon Park, Dongwoo Kim

CoRR, March, 2026

Posterior Label Smoothing for Node Classification.

Jaeseung Heo, MoonJeong Park, Dongwoo Kim

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025

Influence Functions for Edge Edits in Non-Convex Graph Neural Networks.

Jaeseung Heo, Kyeongheung Yun, Seokwon Yoon, Moonjeong Park, Jungseul Ok, Dongwoo Kim

CoRR, June, 2025

The Oversmoothing Fallacy: A Misguided Narrative in GNN Research.

MoonJeong Park, Sunghyun Choi, Jaeseung Heo, Eunhyeok Park, Dongwoo Kim

CoRR, June, 2025

2024

Distinguishing Neighborhood Representations Through Reverse Process of GNNs for Heterophilic Graphs.

Moon Jeong Park, Jaeseung Heo, Dongwoo Kim

CoRR, 2024

EPIC: Graph Augmentation with Edit Path Interpolation via Learnable Cost.

Jaeseung Heo, Seungbeom Lee, Sungsoo Ahn, Dongwoo Kim

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024

Mitigating Oversmoothing Through Reverse Process of GNNs for Heterophilic Graphs.

Moonjeong Park, Jaeseung Heo, Dongwoo Kim

Proceedings of the Forty-first International Conference on Machine Learning, 2024