GeoMAE : Masking representation learning for spatio-temporal graph forecasting with missing values

Songyu Ke

doi:10.1016/j.neunet.2026.108986

GeoMAE : Masking representation learning for spatio-temporal graph forecasting with missing values

2026-04-18

0

PRE

AI

DOI：10.1016/j.neunet.2026.108986

Original

Original request for help

Save

Abstract

En 中文

The ubiquity of missing data in urban intelligence systems, attributable to adverse environmental conditions and equipment failures, poses a significant challenge to the efficacy of downstream applications, notably in the realms of traffic forecasting and energy consumption prediction. Therefore, it is imperative to develop a robust spatio-temporal learning methodology capable of extracting meaningful insights from incomplete datasets. Despite the existence of methodologies for spatio-temporal graph forecasting in the presence of missing values, unresolved issues persist.

Keywords:

missing data

spatio-temporal graph forecasting

representation learning

urban intelligence

mask modeling

GeoMAE : Masking representation learning for spatio-temporal graph forecasting with missing values

Abstract

Journal

Organization