An official website of the United States government
We present the Temporal Graph Benchmark (TGB), a collection of challenging and diverse benchmark datasets for realistic, reproducible, and robust evaluation of machine learning models on temporal graphs. TGB datasets are of large scale, spanning years in duration, incorporate both node and edge-level prediction tasks and cover a diverse set of domains including social, trade, transaction, and transportation networks. For both tasks, we design evaluation protocols based on realistic use-cases. We extensively benchmark each dataset and find that the performance of common models can vary drastically across datasets. In addition, on dynamic node property prediction tasks, we show that simple methods often achieve superior performance compared to existing temporal graph models. We believe that these findings open up opportunities for future research on temporal graphs. Finally, TGB provides an automated machine learning pipeline for reproducible and accessible temporal graph research, including data loading, experiment setup and performance evaluation. TGB will be maintained and updated on a regular basis and welcomes community feedback. TGB datasets, data loaders, example codes, evaluation setup, and leaderboards are publicly available at https://tgb.complexdatalab.com/.
more »
« less
This content will become publicly available on December 1, 2026
A powerful lens for temporal network analysis: temporal motifs
More Like this
-
-
The widespread use of Artificial Intelligence (AI) has highlighted the importance of understanding AI model behavior. This understanding is crucial for practical decision-making, assessing model reliability, and ensuring trustworthiness. Interpreting time series forecasting models faces unique challenges compared to image and text data. These challenges arise from the temporal dependencies between time steps and the evolving importance of input features over time. My thesis focuses on addressing these challenges by aiming for more precise explanations of feature interactions, uncovering spatiotemporal patterns, and demonstrating the practical applicability of these interpretability techniques using real-world datasets and state-of-the-art deep learning models.more » « less
-
Temporal logics cover important classes of system specifications dealing with system behavior over time. Despite the prevalence of long-running systems that accept repeated input and output, and thus the clear relevance of temporal specifications to training software engineers, temporal logics are rarely taught to undergraduates. We motivate and describe an approach to teaching temporal specifications and temporal reasoning indirectly through teaching students about mocking dependencies, which is widely used in software testing of large systems (and therefore of more obvious relevance to students), less notationally intimidating to students, and still teaches similar reasoning principles. We report on 7 years of experience using this indirect approach to behavioral specifications in a software quality course.more » « less
