Skip to content

Patch-based Information Fusion Network

Home / Concepts / Patch-based Information Fusion Network

Patch-based Information Fusion Network

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

A neural architecture for time series forecasting that processes input sequences as local patches and fuses them via a gating mechanism to weight temporal importance.

Why It Matters

It is the core architectural contribution of the paper, enabling multi-scale temporal feature extraction through patching and gated fusion.

Evidence

In the building load forecasting module, we propose the patch-based information fusion network (PIF-Net).

Metadata & Links