Skip to content

Demistifying Data and Simulator Assumptions in Supervised Causal Discovery

Sep 2026 · 0 citations · 54 references
Computer Science

TL;DR

This paper organizes methods by prediction target, prediction granularity, encoder, structural decoder, and training regime to relate what each method predicts to how it uses data and simulator-based supervision, and distinguishes two questions: whether the target is identifiable under the assumed model class and whether a trained predictor generalizes beyond its training distribution.

Abstract

Supervised causal discovery learns to infer causal structure for a new dataset from training datasets paired with structural labels. These training pairs are typically simulated, making the simulator both a source of supervision and a carrier of assumptions about causal graphs, mechanisms, and noise. Understanding the resulting predictions therefore requires examining how these assumptions supplement the information available in observational data, which may be compatible with multiple causal graphs. This paper examines that relationship across representative methods available through June 2026. We organize these methods by prediction target, prediction granularity, encoder, structural decoder, and training regime to relate what each method predicts to how it uses data and simulator-based supervision. Using this framework, we distinguish two questions: whether the target is identifiable under the assumed model class, and whether a trained predictor generalizes beyond its training distribution. Restrictions on mechanisms and noise can make otherwise ambiguous causal directions identifiable, but predictive accuracy under those restrictions does not establish transfer when they change. This distinction motivates evaluation that matches metrics to the identifiable graph target and tests changes in graphs, mechanisms, and noise between training and deployment. Extending such evaluation to real data also requires documenting the external causal evidence and uncertainty behind benchmark reference graphs. Together, these analyses guide method comparison and identify open questions in transfer, test-time adaptation, and uncertainty assessment.

View source

Similar papers

Open access Sep 2026

Causal Machine Learning for Discovering Actionable Insights in Observational Data

A unified causal machine learning framework that integrates structural causal modeling with data-driven estimation techniques to enable robust causal discovery and effect estimation and achieves higher causal discovery accuracy with improved precision and recall of causal edges.

Maria Ulfa, Marwan Alshar'e, Dharmesh Dhabliya et al. · 0 citations

From Causal Structure to Conditional Generation

The results suggest that the architectural prior provides a useful organization of contextual information, while exposure to missing-modality cases is still needed for robust fallback when auxiliary inputs are absent.

Yu-Chen Guan, Chair Pradeep Ravikumar, Bryan Wilder · 0 citations
Preprint Aug 2026

Interpretable Causal Discovery via Causal-Effect Constraints

This work considers the task of conditional causal discovery as a Bayesian inference problem, in which the posterior is targeted over causal graphs and parameters conditional on an event such as a causal-effect constraint, and adapts rare-event estimation techniques to perform inference the joint graph-parameter space.

Cixuan Zhang, Guy Van den Broeck, Benjie Wang · 0 citations
#artificial intelligence Preprint Oct 2026

Structure-agnostic Causal Representation Learning

SaCRL is introduced, a framework that jointly identifies the causal structure and learns the corresponding invariant representation without prior structural knowledge, and provides theoretical guarantees for structure identification, including under random-feature approximation, invariance satisfaction, and out-of-dist...

Arman Behnam, Bing-Hui Wang · 2 citations
#machine learning Preprint Sep 2026

Causal Foundation Models

Causal foundation models are pretrained neural networks that estimate causal quantities, such as the average treatment effect, on entirely new datasets using in-context learning without requiring model updates.

Christopher Stith, Hossein Rahmani, Jesse C. Cresswell · 0 citations

Learning Causal Normalizing Flows from Incomplete Data via Observed-Data Likelihood

MissCNF is introduced, which trains CNFs directly on incomplete data by maximizing the marginal likelihood of each partially observed sample, without discarding rows or constructing a completed dataset, and is compared with two common strategies for handling missing data.

Trung-Dung Hoang, Alceu Bissoto, Tim Flühmann et al. · 0 citations

Related blog posts

MIT News · Artificial Intelligence Sep 29, 2026

Who we become when we talk to machines

Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.