AAAI 2025technical1 citations

Expressive Power of Temporal Message Passing

Przemysław Andrzej Wałęga, Michael Rawson

Abstract

Graph neural networks (GNNs) have recently been adapted to temporal settings, often employing temporal versions of the message-passing mechanism known from GNNs. We divide temporal message passing mechanisms from literature into two main types: global and local, and establish Weisfeiler-Leman characterisations for both. This allows us to formally analyse expressive power of temporal message-passing models. We show that global and local temporal message-passing mechanisms have incomparable expressive power when applied to arbitrary temporal graphs. However, the local mechanism is strictly more expressive than the global mechanism when applied to colour-persistent temporal graphs, whose node colours are initially the same in all time points. Our theoretical findings are supported by experimental evidence, underlining practical implications of our analysis.

BibTeX
@article{Wałęga_Rawson_2025, title={Expressive Power of Temporal Message Passing}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/35396}, DOI={10.1609/aaai.v39i20.35396}, abstractNote={Graph neural networks (GNNs) have recently been adapted to temporal settings, often employing temporal versions of the message-passing mechanism known from GNNs. We divide temporal message passing mechanisms from literature into two main types: global and local, and establish Weisfeiler-Leman characterisations for both. This allows us to formally analyse expressive power of temporal message-passing models. We show that global and local temporal message-passing mechanisms have incomparable expressive power when applied to arbitrary temporal graphs. However, the local mechanism is strictly more expressive than the global mechanism when applied to colour-persistent temporal graphs, whose node colours are initially the same in all time points. Our theoretical findings are supported by experimental evidence, underlining practical implications of our analysis.}, number={20}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Wałęga, Przemysław Andrzej and Rawson, Michael}, year={2025}, month={Apr.}, pages={21000-21008} }