-
Context-aware Graph Causality Inference for Few-Shot Molecular Property Prediction
Paper • 2601.11135 • Published • 1 -
Pre-training Graph Neural Networks on 2D and 3D Molecular Structures by using Multi-View Conditional Information Bottleneck
Paper • 2511.18404 • Published -
Discovering Spatial Correlations of Earth Observations for weather forecasting by using Graph Structure Learning
Paper • 2508.07659 • Published -
Mitigating Degree Bias in Graph Representation Learning with Learnable Structural Augmentation and Structural Self-Attention
Paper • 2504.15075 • Published
AI & ML interests
Graph ML, Graph Learning, Graph Neural Networks, Graph Transformers, Graph Representation Learning
Recent Activity
View all activity
Organization Card
Network Science Lab, The Catholic University of Korea
The Network Science Lab at the Catholic University of Korea (NS Lab @ CUK) investigates a wide range of theories and methods related to the collection, representation, and analysis of networked data. Since its establishment in September 2021, NS Lab @ CUK has been working on various artificial intelligence and machine learning models for networked data, including graph representation learning models and graph neural networks (GNNs). Recently, this group has been interested in self-supervised representation learning of dynamic heterogeneous graphs and attributed graphs using multimodal transformers. NS Lab @ CUK has also applied these models to various applications such as detecting rumor propagation and fake news in social media, predicting research collaborators, estimating collaboration performance, predicting drug effects, etc.
NS Lab @ CUK is recruiting new members with fashion and enthusiasm for artificial intelligence studies. If you would like to join us, please do not hesitate to contact us using the following contact information.
E-mail Addresses
-
Context-aware Graph Causality Inference for Few-Shot Molecular Property Prediction
Paper • 2601.11135 • Published • 1 -
Pre-training Graph Neural Networks on 2D and 3D Molecular Structures by using Multi-View Conditional Information Bottleneck
Paper • 2511.18404 • Published -
Discovering Spatial Correlations of Earth Observations for weather forecasting by using Graph Structure Learning
Paper • 2508.07659 • Published -
Mitigating Degree Bias in Graph Representation Learning with Learnable Structural Augmentation and Structural Self-Attention
Paper • 2504.15075 • Published
models 0
None public yet
datasets 0
None public yet