# Invariance, Causality and Robustness

arXiv: https://arxiv.org/abs/1812.08233 · HTML: https://mlsanity.com/paper/1812.08233/

## Key facts

- Cited by 123 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2018.

## Built on by (most cited first, 30 of 123)

- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [Discovering Invariant Rationales for Graph Neural Networks](https://mlsanity.com/paper/2201.12872/) (2022)
- [Understanding plasticity in neural networks](https://mlsanity.com/paper/2303.01486/) (2023)
- [Handling Distribution Shifts on Graphs: An Invariance Perspective](https://mlsanity.com/paper/2202.02466/) (2022)
- [Automatically Interpreting Millions of Features in Large Language Models](https://mlsanity.com/paper/2410.13928/) (2024)
- [LLM Social Simulations Are a Promising Research Method](https://mlsanity.com/paper/2504.02234/) (2025)
- [Fighting Copycat Agents in Behavioral Cloning from Observation Histories](https://mlsanity.com/paper/2010.14876/) (2020)
- [Discover and Cure: Concept-aware Mitigation of Spurious Correlation](https://mlsanity.com/paper/2305.00650/) (2023)
- [Eliciting Latent Knowledge from Quirky Language Models](https://mlsanity.com/paper/2312.01037/) (2023)
- [On the Adversarial Robustness of Causal Algorithmic Recourse](https://mlsanity.com/paper/2112.11313/) (2021)
- [Out-of-distribution Generalization with Causal Invariant Transformations](https://mlsanity.com/paper/2203.11528/) (2022)
- [Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective](https://mlsanity.com/paper/2111.14820/) (2021)
- [CausalAdv: Adversarial Robustness through the Lens of Causality](https://mlsanity.com/paper/2106.06196/) (2021)
- [Anticipating Performativity by Predicting from Predictions](https://mlsanity.com/paper/2208.07331/) (2022)
- [Mind the Label Shift of Augmentation-based Graph OOD Generalization](https://mlsanity.com/paper/2303.14859/) (2023)
- [FaiRR: Faithful and Robust Deductive Reasoning over Natural Language](https://mlsanity.com/paper/2203.10261/) (2022)
- [Unbiased Faster R-CNN for Single-source Domain Generalized Object Detection](https://mlsanity.com/paper/2405.15225/) (2024)
- [Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization](https://mlsanity.com/paper/2311.11114/) (2023)
- [Gradient Masked Averaging for Federated Learning](https://mlsanity.com/paper/2201.11986/) (2022)
- [Fair Representation Learning through Implicit Path Alignment](https://mlsanity.com/paper/2205.13316/) (2022)
- [Freeze then Train: Towards Provable Representation Learning under Spurious Correlations and Feature Noise](https://mlsanity.com/paper/2210.11075/) (2022)
- [Informativeness and Invariance: Two Perspectives on Spurious Correlations in Natural Language](https://mlsanity.com/paper/2204.04487/) (2022)
- [Causal Deep Learning](https://mlsanity.com/paper/2303.02186/) (2023)
- [On the benefits of representation regularization in invariance based domain generalization](https://mlsanity.com/paper/2105.14529/) (2021)
- [CausPref: Causal Preference Learning for Out-of-Distribution Recommendation](https://mlsanity.com/paper/2202.03984/) (2022)
- [Optimization-based Causal Estimation from Heterogenous Environments](https://mlsanity.com/paper/2109.11990/) (2021)
- [Causal Intervention Improves Implicit Sentiment Analysis](https://mlsanity.com/paper/2208.09329/) (2022)
- [Beyond Predictions in Neural ODEs: Identification and Interventions](https://mlsanity.com/paper/2106.12430/) (2021)
- [Interpolation can hurt robust generalization even when there is no noise](https://mlsanity.com/paper/2108.02883/) (2021)
- [Domain Generalization -- A Causal Perspective](https://mlsanity.com/paper/2209.15177/) (2022)

## 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.