Guardado en:
Detalles Bibliográficos
Autores principales: Anwar, Saif, Griffiths, Nathan, Popham, Thomas, Bhalerao, Abhir
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2503.04509
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910861583450112
author Anwar, Saif
Griffiths, Nathan
Popham, Thomas
Bhalerao, Abhir
author_facet Anwar, Saif
Griffiths, Nathan
Popham, Thomas
Bhalerao, Abhir
contents Recent improvements in the expressive power of spatio-temporal models have led to performance gains in many real-world applications, such as traffic forecasting and social network modelling. However, understanding the predictions from a model is crucial to ensure reliability and trustworthiness, particularly for high-risk applications, such as healthcare and transport. Few existing methods are able to generate explanations for models trained on continuous-time dynamic graph data and, of these, the computational complexity and lack of suitable explanation objectives pose challenges. In this paper, we propose $\textbf{S}$patio-$\textbf{T}$emporal E$\textbf{X}$planation $\textbf{Search}$ (STX-Search), a novel method for generating instance-level explanations that is applicable to static and dynamic temporal graph structures. We introduce a novel search strategy and objective function, to find explanations that are highly faithful and interpretable. When compared with existing methods, STX-Search produces explanations of higher fidelity whilst optimising explanation size to maintain interpretability.
format Preprint
id arxiv_https___arxiv_org_abs_2503_04509
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle STX-Search: Explanation Search for Continuous Dynamic Spatio-Temporal Models
Anwar, Saif
Griffiths, Nathan
Popham, Thomas
Bhalerao, Abhir
Machine Learning
Artificial Intelligence
Recent improvements in the expressive power of spatio-temporal models have led to performance gains in many real-world applications, such as traffic forecasting and social network modelling. However, understanding the predictions from a model is crucial to ensure reliability and trustworthiness, particularly for high-risk applications, such as healthcare and transport. Few existing methods are able to generate explanations for models trained on continuous-time dynamic graph data and, of these, the computational complexity and lack of suitable explanation objectives pose challenges. In this paper, we propose $\textbf{S}$patio-$\textbf{T}$emporal E$\textbf{X}$planation $\textbf{Search}$ (STX-Search), a novel method for generating instance-level explanations that is applicable to static and dynamic temporal graph structures. We introduce a novel search strategy and objective function, to find explanations that are highly faithful and interpretable. When compared with existing methods, STX-Search produces explanations of higher fidelity whilst optimising explanation size to maintain interpretability.
title STX-Search: Explanation Search for Continuous Dynamic Spatio-Temporal Models
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2503.04509