Skip to content

Static-Dynamic Graph Fusion

Home / Concepts / Static-Dynamic Graph Fusion

Static-Dynamic Graph Fusion

Auto-generated stub. Edit this file to add more details.

A dual-path graph learning framework that combines static prior-based graphs with multi-scale, adaptively learned dynamic graphs for multivariate time series forecasting.

Why It Matters

The core novelty of the paper is the specific dual-path graph structure learning that merges static prior knowledge with adaptively learned multi-scale dynamic dependencies.

Evidence

proposes a novel Static-Dynamic Graph Fusion network (SDGF), whose core lies in capturing multi-scale inter-series correlations through a dual-path graph structure learning approach.

Metadata & Links