no code implementations • 4 Mar 2024 • Yinhua Piao, Sangseon Lee, Yijingxiu Lu, Sun Kim
Out-of-distribution (OOD) generalization in the graph domain is challenging due to complex distribution shifts and a lack of environmental contexts.
1 code implementation • 16 May 2023 • Nayeon Kim, Yinhua Piao, Sun Kim
Directly adopting existing hypergraph methods on clinical notes cannot sufficiently utilize the hierarchy information of the patient, which can degrade clinical semantic information by (1) frequent neutral words and (2) hierarchies with imbalanced distribution.
no code implementations • 16 Sep 2022 • Sangseon Lee, Dohoon Lee, Yinhua Piao, Sun Kim
In this paper, we propose Structure Prototype Guided Pooling (SPGP) that utilizes prior graph structures to overcome the limitation.
1 code implementation • 13 Dec 2021 • Yinhua Piao, Sangseon Lee, Dohoon Lee, Sun Kim
To address these challenges, we propose a novel GNN-based sparse structure learning model for inductive document classification.