This page is an archive for papers reviewed by members of the Network Science Lab, along with corresponding presentation materials, as part of the NS-CUK Weekly Seminar series. Launched in Fall 2022, this seminar series is intended to be a platform for the members of the Network Science Lab at the Catholic University of Korea to exchange insights and understanding of state-of-the-art AI methodologies and models for graph mining.
Previous Years
2026
Mar 09th, 2026
T.B.T. Do, Review on "DOTGraph: CLIP-Driven Feature Disentanglement and Optimal Transport based Graph Learning for Few-Shot Segmentation", WACV 2026
H.T. Ho, Review on "Learning Long Range Dependencies on Graphs via Random Walks", ICLR 2025
H.W. Kim, Review on "Learning Condensed Graph via Differentiable Atom Mapping for Reaction Yield Prediction", ICML 2025
J.H. Cho, Review on "Topology-aware Neural Flux Prediction Guided by Physics", arXiv preprint arXiv:2506.05676 2025
S.H. Lee, Review on "Neural Relational Inference for Interacting Systems", ICML 2018 & "Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks", KDD 2020
Feb 23rd, 2026
T.B.T. Do, Review on "Hypergraph Learning for Unsupervised Graph Alignment via Optimal Transport", AAAI 2025
H.W. Kim, Review on "Reaction Graph: Towards Reaction-Level Modeling for Chemical Reactions with 3D Structures", ICML 2025
J.H. Cho, Review on "Universal Physics Transformers: A Framework ForEfficiently Scaling Neural Operators", NeurIPS 2024
S.H. Lee, Review on "PhysDiff: A Physically-Guided Diffusion Model for Multivariate Time Series Anomaly Detection", NeurIPS 2025
Feb 02nd, 2026
T.B.T. Do, Review on "Neurocircuitry-Inspired Hierarchical Graph Causal Attention Networks for Explainable Depression Identification", ICLR 2026
H.W. Kim, Review on "Winner Takes It All: Training Performant RL Populations for Combinatorial Optimization", NeurIPS 2023
Jan 26th, 2026
T.B.T. Do, Review on "MIHC: Multi-View Interpretable Hypergraph Neural Networks with Information Bottleneck for Chip Congestion Prediction", NeurIPS 2025
H.W. Kim, Review on "Incorporating Retrieval-based Causal Learning with Information Bottlenecks for Interpretable Molecular Graph Learning", KDD 2025
J.H. Cho, Review on "Accelerating process synthesis with reinforcement learning: Transfer learning from multi-fidelity simulations and variational autoencoders", Computers & Chemical Engineering 2025
S.H. Lee, Review on "MIHC: Multi-View Interpretable Hypergraph Neural Networks with Information Bottleneck for Chip Congestion Prediction", NeurIPS 2025
Jan 19th, 2026
V.T. Hoang, Review on "Group graph: a molecular graph representation with enhanced performance, efficiency and interpretability", Journal of Cheminformatics 2024
T.B.T. Do, Review on "DHGFormer: Dynamic Hierarchical Graph Transformer for Disorder Brain Disease Diagnosis", MICCAI 2025
H.W. Kim, Review on "Hierarchical Graph Latent Diffusion Model for ConditionalMolecule Generation", CIKM 2025
S.H. Lee, Review on "Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models", deepseek 2026
Jan 12th, 2026
V.T. Hoang, Review on "Multimodal Fusion with Relational Learning for Molecular Property Prediction", Nature Communications Chemistry 2025
T.B.T. Do, Review on "Bipartite Patient-Modality Graph Learning with Event-Conditional Modelling of Censoring for Cancer Survival Prediction", MICCAI 2025
H.W. Kim, Review on "3D Infomax improves GNNs for Molecular Property Prediction", ICML 2022
S.H. Lee, Review on "MAG-GNN: Reinforcement Learning Boosted Graph Neural Network", NeurIPS 2023
Jan 05th, 2026
V.T. Hoang, Review on "MolTC: Towards Molecular Relational Modeling In Language Models", ACL 2024
H.W. Kim, Review on "Shift-Robust Molecular Relational Learning with Causal Substructure", KDD 2023
J.H. Cho, Review on "A Plant-Wide Industrial Process Control Problem", Computers & chemical engineering 1993
