Synthetic Datasets for Machine Learning on Spatio-Temporal Graphs using PDEs

J Arndt, U Isil, M Detzel, W Samek, J Ma - arxiv preprint arxiv:2502.04140, 2025 - arxiv.org
Many physical processes can be expressed through partial differential equations (PDEs).
Real-world measurements of such processes are often collected at irregularly distributed …

TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential Dynamics

L Yi, J Peng, Y Zheng, F Mo, Z Wei, Y Ye… - arxiv preprint arxiv …, 2025 - arxiv.org
Future link prediction is a fundamental challenge in various real-world dynamic systems. To
address this, numerous temporal graph neural networks (temporal GNNs) and benchmark …

Multi-Scale Heterogeneous Text-Attributed Graph Datasets From Diverse Domains

Y Liu, Q **e, J Shi, J Shen, T He - arxiv preprint arxiv:2412.08937, 2024 - arxiv.org
Heterogeneous Text-Attributed Graphs (HTAGs), where different types of entities are not
only associated with texts but also connected by diverse relationships, have gained …

Expressive Power of Temporal Message Passing

PA Wałęga, M Rawson - arxiv preprint arxiv:2408.09918, 2024 - arxiv.org
Graph neural networks (GNNs) have recently been adapted to temporal settings, often
employing temporal versions of the message-passing mechanism known from GNNs. We …