Measure-Theoretic Anti-Causal Representation Learning
Not on the map. Why?
Abstract (arXiv)
Causal representation learning in the anti-causal setting (labels cause features rather than the reverse) presents unique challenges requiring specialized approaches. We propose Anti-Causal Invariant Abstractions (ACIA), a novel measure-theoretic framework for anti-causal representation learning. ACIA employs a two-level design, low-level representations capture how labels generate observations, while high-level representations learn stable causal patterns across environment-specific variations. ACIA addresses key limitations of existing approaches by accommodating prefect and imperfect interventions through interventional kernels, eliminating dependency on explicit causal structures, handling high-dimensional data effectively, and providing theoretical guarantees for out-of-distribution generalization. Experiments on synthetic and real-world medical datasets demonstrate that ACIA consistently outperforms state-of-the-art methods in both accuracy and invariance metrics. Furthermore, our theoretical results establish tight bounds on performance gaps between training and unseen environments, confirming the efficacy of our approach for robust anti-causal learning.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 59 of its 78 references that are in the map. First posted on arXiv 16 Oct 2025.
Builds on
59 of 78 references.
References · 59
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2015Domain-Adversarial Training of Neural Networkscited by 3,023
- 2019Invariant Risk Minimizationcited by 1,832
- 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
- 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
- 2020In Search of Lost Domain Generalizationcited by 1,042
- 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
- 2015Causal inference using invariant prediction: identification and confidence intervalscited by 533
- 2021SWAD: Domain Generalization by Seeking Flat Minimacited by 431
- 2021Causal Abstractions of Neural Networkscited by 401
- 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
- 2016Harmonic Networks: Deep Translation and Rotation Equivariancecited by 293
38 more
- 2021A Fourier-based Framework for Domain Generalizationcited by 287
- 2018Learning Not to Learn: Training Deep Neural Networks with Biased Datacited by 255
- 2020Deep Domain-Adversarial Image Generation for Domain Generalisationcited by 231
- 2021Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalizationcited by 220
- 2019Causality matters in medical imagingcited by 193
- 2019Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathologycited by 172
- 2021Deep Stable Learning for Out-Of-Distribution Generalizationcited by 153
- 2017Invariant Causal Prediction for Nonlinear Modelscited by 140
- 2022Weakly supervised causal representation learningcited by 140
- 2022Interventional Causal Representation Learningcited by 140
- 2022Causality Inspired Representation Learning for Domain Generalizationcited by 136
- 2020Domain Adaptation with Conditional Distribution Matching and Generalized Label Shiftcited by 124
- 2022Disentangled Representation Learningcited by 111
- 2023Nonparametric Identifiability of Causal Representations from Unknown Interventionscited by 105
- 2018Abstracting Causal Modelscited by 104
- 2022Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalizationcited by 97
- 2021Towards a Theoretical Framework of Out-of-Distribution Generalizationcited by 94
- 2023Learning Linear Causal Representations from Interventions under General Nonlinear Mixingcited by 92
- 2022Linear Causal Disentanglement via Interventionscited by 84
- 2021Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Testscited by 77
- 2021Improved OOD Generalization via Adversarial Training and Pre-trainingcited by 66
- 2020Learning Causal Semantic Representation for Out-of-Distribution Predictioncited by 60
- 2023Causal Component Analysiscited by 56
- 2022Causal Structure Learning: a Combinatorial Perspectivecited by 46
- 2021Learning Neural Causal Models with Active Interventionscited by 40
- 2022Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shiftcited by 38
- 2020Active Invariant Causal Prediction: Experiment Selection through Stabilitycited by 37
- 2022Invariant and Transportable Representations for Anti-Causal Domain Shiftscited by 37
- 2023Understanding and Improving Feature Learning for Out-of-Distribution Generalizationcited by 35
- 2023Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalizationcited by 29
- 2023Discovering environments with XRMcited by 26
- 2021Privacy-Preserving Representation Learning on Graphs: A Mutual Information Perspectivecited by 23
- 2023Multi-Domain Causal Representation Learning via Weak Distributional Invariancescited by 23
- 2018Causal Inference via Kernel Deviance Measurescited by 22
- 2023Rethinking the Evaluation Protocol of Domain Generalizationcited by 20
- 2022Learning Latent Causal Dynamicscited by 13
- 2022Improving Adversarial Robustness via Mutual Information Estimationcited by 13
- 2023Task-Agnostic Privacy-Preserving Representation Learning for Federated Learning Against Attribute Inference Attackscited by 13
50 most cited of 59 All 59 (JSON)
Built on by
Citing papers per year: 2026: 3.
3 papers.