The Network Science Lab at the Catholic University of Korea releases Context-Aware Residual Transformer, namely CART, a novel transformer-based recommendation system specialised in offline retail environment.
The Network Science Lab at the Catholic University of Korea releases Community-aware Graph Transformers, namely CGT, a novel Graph Transformer model specialised in mitigating degree biases in message passing mechanism.
The Network Science Lab at the Catholic University of Korea releases LiteralKG, a novel GNN model for learning literal-aware representations of medical knowledge graphs to integrate literal information and graph structural features into unified vector representations.
The Network Science Lab at the Catholic University of Korea releases UGT, a novel Graph Transformer model specialised in preserving both local and global graph structures.
The Network Science Lab at the Catholic University of Korea releases Connector, a comprehensive graph representation learning framework developed primarily in Python using the PyTorch library.