What is it about?
We introduce STMAE, a self-supervised learning method using masked autoencoders to enhance various spatial-temporal models for traffic forecasting, mitigating data scarcity and incompleteness concerns.
Featured Image
Why is it important?
STMAE offers seamless integration to existing models without needing complex data augmentation, positioning itself as a flexible and powerful enhancement tool for traffic forecasting.
Read the Original
This page is a summary of: Revealing the Power of Masked Autoencoders in Traffic Forecasting, October 2024, ACM (Association for Computing Machinery),
DOI: 10.1145/3627673.3679989.
You can read the full text:
Contributors
The following have contributed to this page
