Realization of Causal Representation Learning to Adjust Confounding Bias in Latent Space
Preprint
Abstract
Applying Deep Learning (DL) models to graphical causal learning has brought outstanding effectiveness and efficiency but is still far from widespread use in domain sciences. In research of EHR (Electronic Healthcare Records), we realize that some confounding bias inherently exists in the causally formed data, which DL cannot automatically adjust. Trace to the source is because the Acyclic Causal Graph can be Multi-Dimensional, so the bias and causal learning happen in two subspaces, which makes it unobservable from the learning process. This paper initially raises the concept of Dimensionality for causal graphs. In our case, the 3-Dimensional DAG (Directed Acyclic Graph) space is defined by the axes of causal variables, the Absolute timeline, and Relative timelines; This is also the essential difference between Causality and Correlation problems. We propose a novel new framework Causal Representation Learning (CRL), to realize Graphical Causal Learning in latent space, which aims to provide general solutions for 1) the inherent bias adjustment and 2) the DL causal models generalization problem. We will also demonstrate the realization of CRL with originally designed architecture and experimentally confirm its feasibility.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Unsuitability of NOTEARS for Causal Graph Discovery when Dealing with Dimensional QuantitiesNeural Processing Letters, 2022
- Causal Discovery in Manufacturing: A Structured Literature ReviewJournal of Manufacturing and Materials Processing, 2022
- Sequence-to-Sequence Learning for Prediction of Soil Temperature and MoistureIEEE Geoscience and Remote Sensing Letters, 2022
- When causal inference meets deep learningNature Machine Intelligence, 2020
- Evaluation of Methods for Causal Discovery in Hydrometeorological SystemsWater Resources Research, 2020
- Debates—Does Information Theory Provide a New Paradigm for Earth Science? Causality, Interaction, and FeedbackWater Resources Research, 2020
- Review of Causal Discovery Methods Based on Graphical ModelsFrontiers in Genetics, 2019
- Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networksHydrology and Earth System Sciences, 2018
- An overview on data representation learning: From traditional feature learning to recent deep learningThe Journal of Finance and Data Science, 2016
- The lesson of causal discovery algorithms for quantum correlations: causal explanations of Bell-inequality violations require fine-tuningNew Journal of Physics, 2015