DeepAI
Log In Sign Up

Latent Causal Invariant Model

11/04/2020
by   Xinwei Sun, et al.
0

Current supervised learning can learn spurious correlation during the data-fitting process, imposing issues regarding interpretability, out-of-distribution (OOD) generalization, and robustness. To avoid spurious correlation, we propose a Latent Causal Invariance Model (LaCIM) which pursues causal prediction. Specifically, we introduce latent variables that are separated into (a) output-causative factors and (b) others that are spuriously correlated to the output via confounders, to model the underlying causal factors. We further assume the generating mechanisms from latent space to observed data to be causally invariant. We give the identifiable claim of such invariance, particularly the disentanglement of output-causative factors from others, as a theoretical guarantee for precise inference and avoiding spurious correlation. We propose a Variational-Bayesian-based method for estimation and to optimize over the latent space for prediction. The utility of our approach is verified by improved interpretability, prediction power on various OOD scenarios (including healthcare) and robustness on security.

READ FULL TEXT

page 8

page 30

02/02/2022

Invariant Ancestry Search

Recently, methods have been proposed that exploit the invariance of pred...
09/19/2020

Causal Discovery with Multi-Domain LiNGAM for Latent Factors

Discovering causal structures among latent factors from observed data is...
03/29/2021

Bayesian Attention Networks for Data Compression

The lossless data compression algorithm based on Bayesian Attention Netw...
06/23/2022

Invariant Causal Mechanisms through Distribution Matching

Learning representations that capture the underlying data generating pro...
07/20/2022

Structural Causal 3D Reconstruction

This paper considers the problem of unsupervised 3D object reconstructio...
05/07/2019

Unified Adversarial Invariance

We present a unified invariance framework for supervised neural networks...
11/29/2021

Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective

Learning behavioral patterns from observational data has been a de-facto...