Causal Counterfactual Generation

Follow this topic Ask about this topic

Causal counterfactual generation asks what would have happened to the same unit or system under a different action, treatment, or feature value. Methods often use structural causal models and abduction-action-prediction, alongside latent-variable models, optimal transport, flow matching, and diffusion to generate alternatives in images, time series, text, and interactive worlds. Work also builds benchmarks with known interventions or paired outcomes to test causal validity, realism, preservation of unchanged features, and performance under distribution shift. A central challenge is balancing plausible, localized edits with faithful causal mechanisms, especially when counterfactuals are not identifiable from observational data alone.

Latest papers

47 papers6 papers in the last four weeks, down 40% on the four weeks before. 0.0% of all new papers.

Content-Style Identification via Differential Independence
May 18, 2026Subash Timilsina, Hoang-Son Nguyen, Sagar Shrestha +1Representation Identifiability Causal Counterfactual Generation
School of Electrical Engineering and Computer Science, Oregon State University, Corvallis, Oregon, USA.
A General Bézier Tree Encoding Counterfactual Framework for Retinal-Vessel-Mediated Disease Analysis
May 13, 2026Tan Su, Ethan Elio Meidinger, Lin Gu +1Medical Image Analysis Causal Counterfactual Generation
Department of Electronic and Electrical Engineering, Southern University of Science and Technology · School of Data Science,University of Virginia, Charlottesville · Research Institute of Electrical Communication, Tohoku University +1
Extended Wasserstein-GAN Approach to Causal Distribution Learning: Density-Free Estimation and Minimax Optimality
May 11, 2026Shu Tamano, Masaaki ImaizumiCausal Effect Estimation Causal Counterfactual Generation
1The University of Tokyo · 2Japan Institute for Health Security · 3RIKEN Center for Advanced Intelligence Project +1
Debiased Counterfactual Generation via Flow Matching from Observations
May 8, 2026Hugh Dance, Johnny Xi, Peter Orbanz +1Flow Matching Causal Counterfactual Generation
Gatsby Computational Neuroscience Unit University College London · Department of Statistics University of British Columbia
Seeing What Shouldn't Be There: Counterfactual GANs for Medical Image Attribution
May 6, 2026Shakeeb MurtazaFeature Attribution Counterfactual Explanations
COMSATS University Islamabad
Counterfactual identifiability beyond global monotonicity: non-monotone triangular structural causal models
May 6, 2026Pengcheng Tan, Jiang Chen, Dehui DuStructural Causal Models Causal Counterfactual Generation
Shanghai Key Laboratory of Trustworthy Computing, East China Normal University
TabSCM: A practical Framework for Generating Realistic Tabular Data
Apr 24, 2026Sven Jacob, Bardh Prenkaj, Weijia Shao +1Structural Causal Models Causal Counterfactual Generation
Federal Institute for Occupational Safety and Health (BAuA), Dresden, Germany · School of Computation, Information and Technology, Technical University of Munich, Munich, Germany · Munich Center for Machine Learning (MCML)
Towards Counterfactual Explanation and Assertion Inference for CPS Debugging
Apr 9, 2026Zaid Ghazal, Hadiza Yusuf, Khouloud GaaloulCyber-Physical Systems Counterfactual Explanations
University of Michigan-Dearborn, Dearborn, MI, USA
Wasserstein Parallel Transport for Predicting the Dynamics of Statistical Systems
Mar 24, 2026Tristan Luca Saidi, Gonzalo Mena, Larry Wasserman +1Batch Effect Correction Causal Counterfactual Generation
Department of Statistics and Data Science, Carnegie Mellon University · Machine Learning Department, Carnegie Mellon University · Department of Economics, Emory University
CounterScene: Counterfactual Causal Reasoning in Generative World Models for Safety-Critical Closed-Loop Evaluation
Mar 22, 2026Bowen Jing, Ruiyang Hao, Weitao Zhou +1Autonomous Driving Scenario Generation Adversarial Scenario Generation
Tuojing Intelligence · King’s College London · Tsinghua University +1
The Causal Uncertainty Principle: Manifold Tearing and the Topological Limits of Counterfactual Interventions
Mar 18, 2026Rui Wu, Hong Xie, Yongjun LiCausal Intervention Causal Inference
School of Management, University of Science and Technology of China 96 Jinzhai Road, Hefei, 230026, Anhui, China · School of Computer Science and Engineering, University of Science and Technology of China 96 Jinzhai Road, Hefei, 230026, Anhui, China
Cohomological Obstructions to Global Counterfactuals: A Sheaf-Theoretic Foundation for Generative Causal Models
Mar 18, 2026Rui Wu, Hong Xie, Yongjun LiCausal Counterfactual Generation Causal Inference
School of Management, University of Science and Technology of China · School of Computer Science and Engineering, University of Science and Technology of China
Modeling Matches as Language: A Generative Transformer Approach for Counterfactual Player Valuation in Football
Mar 16, 2026Miru Hong, Minho Lee, Geonhee Jo +4Autoregressive Transformer Counterfactual Prediction
University of Seoul, Seoul, Republic of Korea · Saarland University, Saarbrücken, Germany · KAIST, Daejeon, Republic of Korea +2
Sequential Transport for Causal Mediation Analysis
Mar 16, 2026Agathe Fernandes Machado, Iryna Voitsitska, Arthur Charpentier +1Causal Mediation Analysis Causal Attribution
Université du Québec à Montréal (UQAM), Canada · Ukrainian Catholic University, Ukraine · Kyoto University, Japan +2
Mask-Guided Attention Regulation for Anatomically Consistent Counterfactual CXR Synthesis
Mar 4, 2026Zichun Zhang, Weizhi Nie, Honglin Guo +1Medical Image Synthesis Diffusion-Based Image Editing
Tianjin University
Federated Causal Representation Learning in State-Space Systems for Decentralized Counterfactual Reasoning
Feb 23, 2026Nazal Mohamed, Ayush Mohanty, Nagi GebraeelCausal Representation Learning Causal Counterfactual Generation
Georgia Institute of Technology, Atlanta, GA
CEPAE: Conditional Entropy-Penalized Autoencoders for Time Series Counterfactuals
Feb 17, 2026Tomàs Garriga, Gerard Sanz, Eduard Serrahima de Cambra +1Causal Counterfactual Generation Causal Inference
Novartis · Barcelona Supercomputing Center

May 18, 2026J/K move · Enter open · S save

Content-Style Identification via Differential Independence

Subash Timilsina, Hoang-Son Nguyen, Sagar Shrestha, Xiao Fu

School of Electrical Engineering and Computer Science, Oregon State University, Corvallis, Oregon, USA.

Representation Identifiability Causal Counterfactual Generation Representation Disentanglement

Open paper AskPDF arXiv

Generative analysis often models multi-domain observations as nonlinear mixtures of domain-invariant content variables and domain-specific style variables. Identifying both factors from unpaired domains enables tasks such as domain transfer and counterfactual data generation. Prior work establishes identifiability under (block-wise) statistical independence between content and style, or via sparse Jacobian assumptions on the nonlinear mixing function, but such conditions can be restrictive in practice. In this work, we introduce content-style differential independence (CSDI), an alternative structural condition requiring that infinitesimal variations in content and style induce orthogonal directions on the data manifold, thereby enabling identifiability even when content and style are dependent and the Jacobian is dense. We operationalize this condition through a blockwise orthogonality constraint on the Jacobian subspaces associated with content and style. To support high-dimensional generative models, we design a stochastic regularizer based on numerical Jacobian approximation, enabling scalable training in settings such as high-resolution image generation. Experiments across multiple datasets corroborate the identifiability analysis and demonstrate practical benefits on counterfactual generation and domain translation.