Generalization in anti-causal learning

TL;DR

This paper argues that incorporating causal models into supervised learning enhances generalization by enabling hypothesis validation, especially in anti-causal tasks where traditional methods often fail beyond standard i.i.d. settings.

Contribution

It introduces a framework emphasizing the importance of causal models for hypothesis search and validation in anti-causal learning, challenging current inference-only approaches.

Findings

Anti-causal tasks require causal models for effective generalization.

Incorporating causal validation improves robustness against adversarial attacks.

Theoretical and literature evidence supports causal integration in supervised learning.

Abstract

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.