English

Do We Need an Encoder-Decoder to Model Dynamical Systems on Networks?

Machine Learning 2023-05-23 v1 Artificial Intelligence

Abstract

As deep learning gains popularity in modelling dynamical systems, we expose an underappreciated misunderstanding relevant to modelling dynamics on networks. Strongly influenced by graph neural networks, latent vertex embeddings are naturally adopted in many neural dynamical network models. However, we show that embeddings tend to induce a model that fits observations well but simultaneously has incorrect dynamical behaviours. Recognising that previous studies narrowly focus on short-term predictions during the transient phase of a flow, we propose three tests for correct long-term behaviour, and illustrate how an embedding-based dynamical model fails these tests, and analyse the causes, particularly through the lens of topological conjugacy. In doing so, we show that the difficulties can be avoided by not using embedding. We propose a simple embedding-free alternative based on parametrising two additive vector-field components. Through extensive experiments, we verify that the proposed model can reliably recover a broad class of dynamics on different network topologies from time series data.

Keywords

Cite

@article{arxiv.2305.12185,
  title  = {Do We Need an Encoder-Decoder to Model Dynamical Systems on Networks?},
  author = {Bing Liu and Wei Luo and Gang Li and Jing Huang and Bo Yang},
  journal= {arXiv preprint arXiv:2305.12185},
  year   = {2023}
}

Comments

Accepted by IJCAI 2023

R2 v1 2026-06-28T10:40:02.668Z