DeepAI AI Chat
Log In Sign Up

The Causal Loss: Driving Correlation to Imply Causation

by   Moritz Willig, et al.

Most algorithms in classical and contemporary machine learning focus on correlation-based dependence between features to drive performance. Although success has been observed in many relevant problems, these algorithms fail when the underlying causality is inconsistent with the assumed relations. We propose a novel model-agnostic loss function called Causal Loss that improves the interventional quality of the prediction using an intervened neural-causal regularizer. In support of our theoretical results, our experimental illustration shows how causal loss bestows a non-causal associative model (like a standard neural net or decision tree) with interventional capabilities.


page 1

page 2

page 3

page 4


A Loss-Function for Causal Machine-Learning

Causal machine-learning is about predicting the net-effect (true-lift) o...

CILF:Causality Inspired Learning Framework for Out-of-Distribution Vehicle Trajectory Prediction

Trajectory prediction is critical for autonomous driving vehicles. Most ...

Causality Networks

While correlation measures are used to discern statistical relationships...

On Image Classification: Correlation v.s. Causality

Image classification is one of the fundamental problems in computer visi...

Causal Regularization

In application domains such as healthcare, we want accurate predictive m...

Causal Future Prediction in a Minkowski Space-Time

Estimating future events is a difficult task. Unlike humans, machine lea...

Grasping Causality for the Explanation of Criticality for Automated Driving

The verification and validation of automated driving systems at SAE leve...