mlsanityData to 7 Oct 2026

Invariance, Causality and Robustness

arXiv 1812.08233 ↗First posted 19 Dec 2018stat.MEcited by 123

Not on the map. Why?

Abstract (arXiv)

We discuss recent work for causal inference and predictive robustness in a unifying way. The key idea relies on a notion of probabilistic invariance or stability: it opens up new insights for formulating causality as a certain risk minimization problem with a corresponding notion of robustness. The invariance itself can be estimated from general heterogeneous or perturbation data which frequently occur with nowadays data collection. The novel methodology is potentially useful in many applications, offering more robustness and better `causal-oriented' interpretation than machine learning or estimation in standard regression or classification frameworks.

Key facts. Cited by 123 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 18; 2022: 30; 2023: 34; 2024: 8; 2025: 18; 2026: 14.

123 papers.

Sort:

By area:

  1. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  2. 2022Discovering Invariant Rationales for Graph Neural Networkscited by 186
  3. 2023Understanding plasticity in neural networkscited by 170
  4. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 163
  5. 2024Automatically Interpreting Millions of Features in Large Language Modelscited by 106
  6. 2025LLM Social Simulations Are a Promising Research Methodcited by 97
  7. 2023Discover and Cure: Concept-aware Mitigation of Spurious Correlationcited by 71
  8. 2020Fighting Copycat Agents in Behavioral Cloning from Observation Historiescited by 70
  9. 2021On the Adversarial Robustness of Causal Algorithmic Recoursecited by 56
  10. 2023Eliciting Latent Knowledge from Quirky Language Modelscited by 56
  11. 2022Out-of-distribution Generalization with Causal Invariant Transformationscited by 45
  12. 2021Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspectivecited by 40
38 more
  1. 2021CausalAdv: Adversarial Robustness through the Lens of Causalitycited by 37
  2. 2022Anticipating Performativity by Predicting from Predictionscited by 37
  3. 2023Mind the Label Shift of Augmentation-based Graph OOD Generalizationcited by 34
  4. 2022FaiRR: Faithful and Robust Deductive Reasoning over Natural Languagecited by 29
  5. 2024Unbiased Faster R-CNN for Single-source Domain Generalized Object Detectioncited by 29
  6. 2023Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalizationcited by 26
  7. 2022Gradient Masked Averaging for Federated Learningcited by 22
  8. 2022Fair Representation Learning through Implicit Path Alignmentcited by 22
  9. 2022Freeze then Train: Towards Provable Representation Learning under Spurious Correlations and Feature Noisecited by 22
  10. 2022Informativeness and Invariance: Two Perspectives on Spurious Correlations in Natural Languagecited by 21
  11. 2023Causal Deep Learningcited by 20
  12. 2021On the benefits of representation regularization in invariance based domain generalizationcited by 17
  13. 2022CausPref: Causal Preference Learning for Out-of-Distribution Recommendationcited by 17
  14. 2021Optimization-based Causal Estimation from Heterogenous Environmentscited by 16
  15. 2022Causal Intervention Improves Implicit Sentiment Analysiscited by 16
  16. 2021Beyond Predictions in Neural ODEs: Identification and Interventionscited by 15
  17. 2021Interpolation can hurt robust generalization even when there is no noisecited by 15
  18. 2022Domain Generalization -- A Causal Perspectivecited by 14
  19. 2023Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selectioncited by 14
  20. 2023Domain Generalisation via Risk Distribution Matchingcited by 14
  21. 2022Characterization and Greedy Learning of Gaussian Structural Causal Models under Unknown Interventionscited by 12
  22. 2024LCA-on-the-Line: Benchmarking Out-of-Distribution Generalization with Class Taxonomiescited by 12
  23. 2025Towards Interpretable Deep Generative Models via Causal Representation Learningcited by 12
  24. 2021Out-of-Distribution Generalization Analysis via Influence Functioncited by 11
  25. 2022Towards out of distribution generalization for problems in mechanicscited by 11
  26. 2023Bivariate Causal Discovery using Bayesian Model Selectioncited by 11
  27. 2022Learning Counterfactually Invariant Predictorscited by 10
  28. 2023Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularizationcited by 10
  29. 2022Finding Diverse and Predictable Subgraphs for Graph Domain Generalizationcited by 9
  30. 2023Causality Guided Disentanglement for Cross-Platform Hate Speech Detectioncited by 9
  31. 2021Operationalizing Complex Causes: A Pragmatic View of Mediationcited by 8
  32. 2023Grounded Image Text Matching with Mismatched Relation Reasoningcited by 8
  33. 2023Debiasing Recommendation by Learning Identifiable Latent Confounderscited by 7
  34. 2023Intervention Generalization: A View from Factor Graph Modelscited by 7
  35. 2022Vision Paper: Causal Inference for Interpretable and Robust Machine Learning in Mobility Analysiscited by 6
  36. 2023Hierarchical Disentanglement-Alignment Network for Robust SAR Vehicle Recognitioncited by 6
  37. 2023PEACE: Cross-Platform Hate Speech Detection- A Causality-guided Frameworkcited by 6
  38. 2024Progression: an extrapolation principle for regressioncited by 6

50 most cited of 123 All 123 (JSON)