# Generalization in anti-causal learning

arXiv: https://arxiv.org/abs/1812.00524 · HTML: https://mlsanity.com/paper/1812.00524/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2018.

## Built on by (most cited first, 23 of 23)

- [MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models](https://mlsanity.com/paper/2309.12284/) (2023)
- [Towards Causal Representation Learning](https://mlsanity.com/paper/2102.11107/) (2021)
- [Diffusion Causal Models for Counterfactual Estimation](https://mlsanity.com/paper/2202.10166/) (2022)
- [Desiderata for Representation Learning: A Causal Perspective](https://mlsanity.com/paper/2109.03795/) (2021)
- [Causal Machine Learning for Healthcare and Precision Medicine](https://mlsanity.com/paper/2205.11402/) (2022)
- [Visual Representation Learning Does Not Generalize Strongly Within the Same Domain](https://mlsanity.com/paper/2107.08221/) (2021)
- [CausalAdv: Adversarial Robustness through the Lens of Causality](https://mlsanity.com/paper/2106.06196/) (2021)
- [Invariant and Transportable Representations for Anti-Causal Domain Shifts](https://mlsanity.com/paper/2207.01603/) (2022)
- [Invariant Learning via Probability of Sufficient and Necessary Causes](https://mlsanity.com/paper/2309.12559/) (2023)
- [Adversarial Visual Robustness by Causal Intervention](https://mlsanity.com/paper/2106.09534/) (2021)
- [Structural Causal 3D Reconstruction](https://mlsanity.com/paper/2207.10156/) (2022)
- [A Holistic Assessment of the Reliability of Machine Learning Systems](https://mlsanity.com/paper/2307.10586/) (2023)
- [Nonuniform Negative Sampling and Log Odds Correction with Rare Events Data](https://mlsanity.com/paper/2110.13048/) (2021)
- [On Causality in Domain Adaptation and Semi-Supervised Learning: an Information-Theoretic Analysis for Parametric Models](https://mlsanity.com/paper/2205.04641/) (2022)
- [Identifying Causal Direction via Dense Functional Classes](https://mlsanity.com/paper/2509.00538/) (2025)
- [Beyond traditional assumptions in fair machine learning](https://mlsanity.com/paper/2101.12476/) (2021)
- [CoLiDR: Concept Learning using Aggregated Disentangled Representations](https://mlsanity.com/paper/2407.19300/) (2024)
- [A step towards the applicability of algorithms based on invariant causal learning on observational data](https://mlsanity.com/paper/2304.02286/) (2023)
- [Is Generation Required for Data-Efficient Perception?](https://mlsanity.com/paper/2512.08854/) (2025)
- [Generalizable Information Theoretic Causal Representation](https://mlsanity.com/paper/2202.08388/) (2022)
- [On Computational Mechanisms for Shared Intentionality, and Speculation on Rationality and Consciousness](https://mlsanity.com/paper/2306.13657/) (2023)
- [Measuring the Effect of Causal Disentanglement on the Adversarial Robustness of Neural Network Models](https://mlsanity.com/paper/2308.10708/) (2023)
- [Parameter Estimation using Reinforcement Learning Causal Curiosity: Limits and Challenges](https://mlsanity.com/paper/2505.08453/) (2025)

## Abstract (arXiv)

The ability to learn and act in novel situations is still a prerogative of animate intelligence, as current machine learning methods mostly fail when moving beyond the standard i.i.d. setting. What is the reason for this discrepancy? Most machine learning tasks are anti-causal, i.e., we infer causes (labels) from effects (observations). Typically, in supervised learning we build systems that try to directly invert causal mechanisms. Instead, in this paper we argue that strong generalization capabilities crucially hinge on searching and validating meaningful hypotheses, requiring access to a causal model. In such a framework, we want to find a cause that leads to the observed effect. Anti-causal models are used to drive this search, but a causal model is required for validation. We investigate the fundamental differences between causal and anti-causal tasks, discuss implications for topics ranging from adversarial attacks to disentangling factors of variation, and provide extensive evidence from the literature to substantiate our view. We advocate for incorporating causal models in supervised learning to shift the paradigm from inference only, to search and validation.