# Realization of Causal Representation Learning to Adjust Confounding Bias in Latent Space

arXiv: https://arxiv.org/abs/2211.08573 · HTML: https://mlsanity.com/paper/2211.08573/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 44 references that are in the map.
- First posted on arXiv 15 Nov 2022.

## Builds on (most cited first, 15 of 15)

- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [DAGs with NO TEARS: Continuous Optimization for Structure Learning](https://mlsanity.com/paper/1803.01422/) (2018)
- [Gradient-Based Neural DAG Learning](https://mlsanity.com/paper/1906.02226/) (2019)
- [Learning Sparse Nonparametric DAGs](https://mlsanity.com/paper/1909.13189/) (2019)
- [Ethical Machine Learning in Health Care](https://mlsanity.com/paper/2009.10576/) (2020)
- [Secure and Robust Machine Learning for Healthcare: A Survey](https://mlsanity.com/paper/2001.08103/) (2020)
- [Causal Discovery in Physical Systems from Videos](https://mlsanity.com/paper/2007.00631/) (2020)
- [Towards Learning Universal, Regional, and Local Hydrological Behaviors via Machine-Learning Applied to Large-Sample Datasets](https://mlsanity.com/paper/1907.08456/) (2019)
- [Causal Machine Learning for Healthcare and Precision Medicine](https://mlsanity.com/paper/2205.11402/) (2022)
- [word2vec Parameter Learning Explained](https://mlsanity.com/paper/1411.2738/) (2014)
- [Unsuitability of NOTEARS for Causal Graph Discovery](https://mlsanity.com/paper/2104.05441/) (2021)
- [From Principal Subspaces to Principal Components with Linear Autoencoders](https://mlsanity.com/paper/1804.10253/) (2018)
- [Overfitting Mechanism and Avoidance in Deep Neural Networks](https://mlsanity.com/paper/1901.06566/) (2019)
- [An Overview on Data Representation Learning: From Traditional Feature Learning to Recent Deep Learning](https://mlsanity.com/paper/1611.08331/) (2016)
- [A Mechanism for Producing Aligned Latent Spaces with Autoencoders](https://mlsanity.com/paper/2106.15456/) (2021)

## Abstract (arXiv)

Causal DAGs(Directed Acyclic Graphs) are usually considered in a 2D plane. Edges indicate causal effects' directions and imply their corresponding time-passings. Due to the natural restriction of statistical models, effect estimation is usually approximated by averaging the individuals' correlations, i.e., observational changes over a specific time. However, in the context of Machine Learning on large-scale questions with complex DAGs, such slight biases can snowball to distort global models - More importantly, it has practically impeded the development of AI, for instance, the weak generalizability of causal models. In this paper, we redefine causal DAG as do-DAG, in which variables' values are no longer time-stamp-dependent, and timelines can be seen as axes. By geometric explanation of multi-dimensional do-DAG, we identify the Causal Representation Bias and its necessary factors, differentiated from common confounding biases. Accordingly, a DL(Deep Learning)-based framework will be proposed as the general solution, along with a realization method and experiments to verify its feasibility.