JODIE,DyRep,TGAT,TGN,CAWN,EdgeBank,TCL,GraphMixer,DyGFormer. Transductive Dynamic Link Prediction For training a model for transductive dynamic link property prediction on a dataset, you can use the following command: dataset="tgbl-wiki" model="GraphMixer" python train_tgb_lpp.py --dataset_nam...
Overview of the Temporal Graph Benchmark (TGB) pipeline: TGB includes large-scale and realistic datasets from five different domains with both dynamic link prediction and node property prediction tasks. TGB automatically downloads datasets and processes them into numpy, PyTorch and PyG compatible Tempor...
Temporal Graph Benchmark TGB is a collection of challenging and diverse benchmark datasets for realistic, reproducible, and robust evaluation for machine learning on temporal graphs. TGB includes both dynamic link and node property prediction tasks and an automated pipeline from dataset downloading, data...
The TGB-Seq benchmark is designed to provide a comprehensive evaluation framework for temporal graph neural networks (GNNs), focusing on their ability to capture complex sequential dynamics. TGB-Seq offers datasets curated from diverse real-world dynamic interaction systems, inherently featuring intricate...
Temporal Graph Learning Models The following continuous-time dynamic graph models can be utilized as TGB baselines for dynamic link property prediction task: JODIE, DyRep, TGAT, TGN, CAWN, EdgeBank, TCL, GraphMixer, DyGFormer. Transductive Dynamic Link Prediction For training a model for transducti...