Temporal graph benchmark for machine learning on temporal graphs

S Huang, F Poursafaei, J Danovitch… - Advances in …, 2023 - proceedings.neurips.cc
Abstract We present the Temporal Graph Benchmark (TGB), a collection of challenging and
diverse benchmark datasets for realistic, reproducible, and robust evaluation of machine …

Evaluating graph neural networks for link prediction: Current pitfalls and new benchmarking

J Li, H Shomer, H Mao, S Zeng, Y Ma… - Advances in …, 2023 - proceedings.neurips.cc
Link prediction attempts to predict whether an unseen edge exists based on only a portion of
the graph. A flurry of methods has been created in recent years that attempt to make use of …

Towards foundation models for knowledge graph reasoning

M Galkin, X Yuan, H Mostafa, J Tang, Z Zhu - ar** machine learning models that respect the
structure and symmetries of eigenvectors. These works promote sign invariance, since for …

Revisiting link prediction: A data perspective

H Mao, J Li, H Shomer, B Li, W Fan, Y Ma… - arxiv preprint arxiv …, 2023 - arxiv.org
Link prediction, a fundamental task on graphs, has proven indispensable in various
applications, eg, friend recommendation, protein analysis, and drug interaction prediction …

Diffusion-based negative sampling on graphs for link prediction

TK Nguyen, Y Fang - Proceedings of the ACM Web Conference 2024, 2024 - dl.acm.org
Link prediction is a fundamental task for graph analysis with important applications on the
Web, such as social network analysis and recommendation systems,\etc\Modern graph link …

Foundation models for the electric power grid

HF Hamann, B Gjorgiev, T Brunschwiler, LSA Martins… - Joule, 2024 - cell.com
Foundation models (FMs) currently dominate news headlines. They employ advanced deep
learning architectures to extract structural information autonomously from vast datasets …