Research map / Graph learning / GNN architectures
Less but More: Linear Adaptive Graph Learning Empowering Spatiotemporal Forecasting
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes MAGE, an adaptive graph learning method for spatiotemporal forecasting that aims to be efficient and more expressive than end-to-end adaptive graph learning in STGNNs.
Problem
STGNN performance depends on graph topology quality, but end-to-end adaptive graph learning methods have high computational complexity and limited expressive capacity.
Approach
MAGE is a linear adaptive graph learning approach intended to learn spatiotemporal dependencies efficiently and with greater expressiveness than prior adaptive graph learners; specific mechanism not stated in the available abstract.
Closest papers by meaning
- Over-squashing in Spatiotemporal Graph Neural Networks (NeurIPS 2025 · similarity 0.88)
- Graph-based Forecasting with Missing Data through Spatiotemporal Downsampling (ICML 2024 · similarity 0.88)
- Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecasting (ICLR 2025 · similarity 0.86)
- Towards Dynamic Spatial-Temporal Graph Learning: A Decoupled Perspective (AAAI 2024 · similarity 0.86)
- ST-FiT: Inductive Spatial-Temporal Forecasting with Limited Training Data (AAAI 2025 · similarity 0.86)
- Robust Spatio-Temporal Centralized Interaction for OOD Learning (ICML 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.