On The Temporal Domain of Differential Equation Inspired Graph Neural Networks

Moshe Eliasof, Eldad Haber, Eran Treister, Carola Bibiane Schönlieb

Research output: Contribution to journalConference articlepeer-review

Abstract

Graph Neural Networks (GNNs) have demonstrated remarkable success in modeling complex relationships in graph-structured data. A recent innovation in this field is the family of Differential Equation-Inspired Graph Neural Networks (DE-GNNs), which leverage principles from continuous dynamical systems to model information flow on graphs with built-in properties such as feature smoothing or preservation. However, existing DE-GNNs rely on first or second-order temporal dependencies. In this paper, we propose a neural extension to those pre-defined temporal dependencies. We show that our model, called TDE-GNN, can capture a wide range of temporal dynamics that go beyond typical first or second-order methods, and provide use cases where existing temporal models are challenged. We demonstrate the benefit of learning the temporal dependencies using our method rather than using pre-defined temporal dynamics on several graph benchmarks.

Original languageAmerican English
Pages (from-to)1792-1800
Number of pages9
JournalProceedings of Machine Learning Research
Volume238
StatePublished - 1 Jan 2024
Event27th International Conference on Artificial Intelligence and Statistics, AISTATS 2024 - Valencia, Spain
Duration: 2 May 20244 May 2024

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability

Fingerprint

Dive into the research topics of 'On The Temporal Domain of Differential Equation Inspired Graph Neural Networks'. Together they form a unique fingerprint.

Cite this