Published June 2, 2024 | Version v2
Preprint Open

TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs

Authors/Creators

  • 1. ROR icon Mila - Quebec Artificial Intelligence Institute
  • 2. ROR icon McGill University
  • 3. ROR icon University of Mannheim
  • 4. ROR icon Université de Montréal
  • 5. ROR icon New Jersey Institute of Technology

Contributors

Contact person:

  • 1. ROR icon Mila - Quebec Artificial Intelligence Institute
  • 2. ROR icon McGill University

Description

Multi-relational temporal graphs are powerful tools for modeling real-world data, capturing the evolving and interconnected nature of entities over time. Recently, many novel models are proposed for ML on such graphs intensifing the need for robust evaluation and standardized benchmark datasets. However, the availability of such resources remains scarce and evaluation faces added complexity due to reproducibility issues in experimental protocols. To address these challenges, we introduce Temporal Graph Benchmark 2.0 (TGB 2.0), a novel benchmarking framework tailored for evaluating methods for predicting future links on Temporal Knowledge Graphs and Temporal Heterogeneous Graphs with a focus on large scale datasets, extending the Temporal Graph Benchmark. TGB 2.0 facilitates comprehensive evaluations by presenting eight novel datasets spanning five domains with up to 53 million edges. TGB 2.0 datasets are significantly larger than existing datasets in terms of number of nodes, edges, or timestamps. Additionally, we propose an evaluation framework aimed at unifying the assessment of existing state-of-the-art methods and baselines on these datasets. Through extensive experimentation, we evaluate the performance of these methods, providing valuable insights into their efficacy.
 
 

Files

thgl-forum.zip

Files (17.8 GB)

Name Size Download all
md5:9ed795e1c00c09cec3333927227f13e8
2.4 GB Preview Download
md5:8f3dc7190a0e251842916769b889e466
589.7 MB Preview Download
md5:3b5a30ee935929ea5411cee4079d21a8
1.7 GB Preview Download
md5:acda1521b6c43871cb1b40ff1725f4ed
1.5 GB Preview Download
md5:cf0104eab6908064ffe949aa2d62cca3
152.3 MB Preview Download
md5:3ef419cfced44f00b9078e48d508ce48
15.5 MB Preview Download
md5:3eb574d2672d137c92cf3a2400ce1460
10.6 MB Preview Download
md5:fe9d66c037137e36a57e2bb83505255f
11.4 GB Preview Download

Additional details

Software

Repository URL
https://github.com/JuliaGast/TGB2
Programming language
Python
Development Status
Active