Temporal Graph Benchmark

Challenging and realistic datasets for temporal graph learning

In recent years, significant advances have been made in machine learning on static graphs, accelerated by the availability of public datasets and standardized evaluation protocols, such as the widely adopted Open Graph Benchmark (OGB). However, many real-world systems such as social networks, transportation networks, and financial transaction networks evolve over time with nodes and edges constantly added or deleted. They are often modeled as temporal graphs. Until now, progress in temporal graph …

benchmark graph machine learning thoughts-and-theory