This year, NS-CUK successfully submitted two research papers to the AAAI, which is one of the most prestigious conferences in AI fields, and were accepted.
The first paper, accepted into the main technical track, presents a novel structure-preserving graph transformer. This approach uniquely blends local and global structural features, significantly enhancing the performance in identifying graph structures. Details of this paper are as follows:
- Van Thuy Hoang, O-Joun Lee: Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity. The 38th AAAI Conference on Artificial Intelligence (AAAI 2024), Vancouver, Canada; 02/2024.
The second paper, submitted to the Explainable Machine Learning for Sciences Workshop (XAI4Sci) in conjunction with AAAI 2024, explores the application of explainable graph neural networks in atmospheric state estimation. This research focuses on assessing the importance of meteorological observations for accurate predictions. The paper details are:
- Hyeon-Ju Jeon, Jeon-Ho Kang, In-Hyuk Kwon, O-Joun Lee: Explainable Graph Neural Networks for Observation Impact Analysis in Atmospheric State Estimation. The Explainable Machine Learning for Sciences Workshop (XAI4Sci) held in conjunction with the 38th AAAI Conference on Artificial Intelligence (AAAI 2024), Vancouver, Canada; 02/2024.
