Skip to content

Causally Guided Transformer

Home / Concepts / Causally Guided Transformer

Causally Guided Transformer

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

A transformer architecture that restricts predictive paths to graph-supported causal precursors via hard parent masking.

Why It Matters

It provides a reusable framework for incorporating structural inductive biases into transformer-based forecasting via hard parent masking.

Evidence

integrating an explicit time-lagged causal graph prior with deep sequence modeling

Metadata & Links