Unified-Graph-Transformer
Unified Graph Transformer (UGT) is a novel Graph Transformer model specialised in preserving both local and global graph structures and developed by NS Lab @ CUK based on pure PyTorch backend.
- 28
- Python
- MIT
- 16 mo ago
NSLab-CUK
Network Science Lab, Dept. of Artificial Intelligence, The Catholic University of Korea
Built from NSLab-CUK's public GitHub profile, Bucheon, Rep. of Korea. Not on Take My Repo yet, so there are no posts or updates here.
Unified Graph Transformer (UGT) is a novel Graph Transformer model specialised in preserving both local and global graph structures and developed by NS Lab @ CUK based on pure PyTorch backend.
Subgraph-conditioned Graph Information Bottleneck (S-CGIB) is a novel architecture for pre-training Graph Neural Networks in molecular property prediction and developed by NS Lab, CUK based on pure PyTorch backend.
Community-aware Graph Transformer (CGT) is a novel Graph Transformer model that utilizes community structures to address node degree biases in message-passing mechanism and developed by NS Lab @ CUK based on pure PyTorch backend.
This framework is a novel Ground Penetrating Radar image analysis framework developed by NS Lab @ CUK, integrating a denoising auto-encoder and channel-wise attention into the YOLOv12 backbone to achieve robust and accurate underground barrier detection under noisy and complex subsurface conditions.
Welcome to the Graph Mining (06837-01) class repository for the Department of Artificial Intelligence at the Catholic University of Korea. This platform is dedicated to sharing and archiving lecture materials such as practices, assignments, and sample codes for the class.
Welcome to the Graph Neural Networks (06838-01) class repository for the Department of Artificial Intelligence at the Catholic University of Korea. This platform is dedicated to sharing and archiving lecture materials such as practices, assignments, and sample codes for the class.
Welcome to the Graph Neural Networks (06838-01) class repository for the Department of Artificial Intelligence at the Catholic University of Korea. This platform is dedicated to sharing and archiving lecture materials such as practices, assignments, and sample codes for the class.
Welcome to the Graph Mining (06837-01) class repository for the Department of Artificial Intelligence at the Catholic University of Korea. This platform is dedicated to sharing and archiving lecture materials such as practices, assignments, and sample codes for the class.
Welcome to the Graph Neural Networks (06838-01) class repository for the Department of Artificial Intelligence at the Catholic University of Korea. This platform is dedicated to sharing and archiving lecture materials such as practices, assignments, and sample codes for the class.
Welcome to the Graph Neural Networks (06838-01) class repository for the Department of Artificial Intelligence at the Catholic University of Korea. This platform is dedicated to sharing and archiving lecture materials such as practices, assignments, and sample codes for the class.
MRER: Mitigating Alignment Bias in Multimodal Sentiment Analysis via Reliability-Aware Fusion and Evidence-Preserving Reconstruction
This study introduces a dual-mode methodology for quantifying pipe corrosion by employing ultrasound technology in conjunction with convolutional neural networks (CNN).
LiteralKG is a novel Attributed Knowledge Graph Embedding Model developed by NS Lab @ CUK based on pure PyTorch backend.
Welcome to the Graph Mining (06837-01) class repository for the Department of Artificial Intelligence at the Catholic University of Korea. This platform is dedicated to sharing and archiving lecture materials such as practices, assignments, and sample codes for the class.
Context-Aware Residual Transformer (CART) is a kiosk recommendation system (CART) that utilizes self-supervised learning techniques tailored to kiosks in an offline retail environment and developed by a collaboration between NS Lab @ CUK and IIP Lab @ Gachon University based on pure PyTorch backend.
Halal or Not is a novel Attributed Knowledge Graph Completion Model developed by NS Lab @ CUK based on pure PyTorch backend. This model aims at analyzing ingredients of everyday products to predict their cultural availability, e.g. predicting whether food or cosmetics meet halal or vegan criteria.
Welcome to the Graph Mining (06837-01) class repository for the Department of Artificial Intelligence at the Catholic University of Korea. This platform is dedicated to sharing and archiving lecture materials such as practices, assignments, and sample codes for the class.
This repository contains the code, intermediate results, and analysis materials for the study: Cross-Context Topic Evolution and Sentiment Dynamics of AI Discourse on Weibo and Twitter.
Multi-View Conditional Information Bottleneck (MVCIB) is a novel architecture for pre-training Graph Neural Networks on 2D and 3D molecular structures and developed by NS Lab, CUK based on pure PyTorch backend.
ProcGNN is a process-graph learning framework for stream-property prediction, developed at Network Science Lab @ CUK and implemented directly in PyTorch.
CaMol is a novel architecture for predicting molecular property in few-shot scenarios and developed by NS Lab, CUK based on pure PyTorch backend.
Novel2Graph is a novel framework for extracting knowledge graphs from literary texts, which is developed by NS Lab @ CUK.