# Graph Out-of-Distribution Generalization via Causal Intervention

arXiv: https://arxiv.org/abs/2402.11494 · HTML: https://mlsanity.com/paper/2402.11494/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 49 references that are in the map.
- First posted on arXiv 18 Feb 2024.

## Builds on (most cited first, 24 of 24)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [Simple and Deep Graph Convolutional Networks](https://mlsanity.com/paper/2007.02133/) (2020)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019)
- [VAE with a VampPrior](https://mlsanity.com/paper/1705.07120/) (2017)
- [Handling Distribution Shifts on Graphs: An Invariance Perspective](https://mlsanity.com/paper/2202.02466/) (2022)
- [From Local Structures to Size Generalization in Graph Neural Networks](https://mlsanity.com/paper/2010.08853/) (2020)
- [Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data](https://mlsanity.com/paper/2108.01099/) (2021)
- [Size-Invariant Graph Representations for Graph Classification Extrapolations](https://mlsanity.com/paper/2103.05045/) (2021)
- [Generalizing Graph Neural Networks on Out-Of-Distribution Graphs](https://mlsanity.com/paper/2111.10657/) (2021)
- [Subgroup Generalization and Fairness of Graph Neural Networks](https://mlsanity.com/paper/2106.15535/) (2021)
- [Twitch Gamers: a Dataset for Evaluating Proximity Preserving and Structural Role-based Node Embeddings](https://mlsanity.com/paper/2101.03091/) (2021)
- [Structural Re-weighting Improves Graph Domain Adaptation](https://mlsanity.com/paper/2306.03221/) (2023)
- [Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems](https://mlsanity.com/paper/1903.10433/) (2019)
- [Fast and Accurate Anomaly Detection in Dynamic Graphs with a Two-Pronged Approach](https://mlsanity.com/paper/2011.13085/) (2020)

## Built on by (most cited first, 30 of 31)

- [Graph ODEs and Beyond: A Comprehensive Survey on Integrating Differential Equations with Graph Neural Networks](https://mlsanity.com/paper/2503.23167/) (2025)
- [Graph Representation Learning via Causal Diffusion for Out-of-Distribution Recommendation](https://mlsanity.com/paper/2408.00490/) (2024)
- [Leveraging Invariant Principle for Heterophilic Graph Structure Distribution Shifts](https://mlsanity.com/paper/2408.09490/) (2024)
- [Dissecting the Failure of Invariant Learning on Graphs](https://mlsanity.com/paper/2411.02847/) (2024)
- [Multi-Scale Heterogeneous Text-Attributed Graph Datasets From Diverse Domains](https://mlsanity.com/paper/2412.08937/) (2024)
- [CoS: Towards Optimal Event Scheduling via Chain-of-Scheduling](https://mlsanity.com/paper/2511.12913/) (2025)
- [A Survey of Out-of-distribution Generalization for Graph Machine Learning from a Causal View](https://mlsanity.com/paper/2409.09858/) (2024)
- [Evolving Graph Learning for Out-of-Distribution Generalization in Non-stationary Environments](https://mlsanity.com/paper/2511.02354/) (2025)
- [Improving Graph Out-of-distribution Generalization Beyond Causality](https://mlsanity.com/paper/2407.10204/) (2024)
- [Memory-enhanced Invariant Prompt Learning for Urban Flow Prediction under Distribution Shifts](https://mlsanity.com/paper/2412.05534/) (2024)
- [NodeReg: Mitigating the Imbalance and Distribution Shift Effects in Semi-Supervised Node Classification via Norm Consistency](https://mlsanity.com/paper/2503.03211/) (2025)
- [Generalizing GNNs with Tokenized Mixture of Experts](https://mlsanity.com/paper/2602.09258/) (2026)
- [From Subtle to Significant: Prompt-Driven Self-Improving Optimization in Test-Time Graph OOD Detection](https://mlsanity.com/paper/2602.17342/) (2026)
- [Causal Neighbourhood Learning for Invariant Graph Representations](https://mlsanity.com/paper/2602.17934/) (2026)
- [Towards OOD Generalization in Dynamic Graphs via Causal Invariant Learning](https://mlsanity.com/paper/2603.01626/) (2026)
- [SCL-GNN: Towards Generalizable Graph Neural Networks via Spurious Correlation Learning](https://mlsanity.com/paper/2603.08270/) (2026)
- [IENE: Identifying and Extrapolating the Node Environment for Out-of-Distribution Generalization on Graphs](https://mlsanity.com/paper/2406.00764/) (2024)
- [Towards Understanding Link Predictor Generalizability Under Distribution Shifts](https://mlsanity.com/paper/2406.08788/) (2024)
- [Teleporter Theory: A General and Simple Approach for Modeling Cross-World Counterfactual Causality](https://mlsanity.com/paper/2406.11501/) (2024)
- [Score-based Conditional Out-of-Distribution Augmentation for Graph Covariate Shift](https://mlsanity.com/paper/2410.17506/) (2024)
- [Robust OOD Graph Learning via Mean Constraints and Noise Reduction](https://mlsanity.com/paper/2506.19281/) (2025)
- [Subgraph Generation for Generalizing on Out-of-Distribution Links](https://mlsanity.com/paper/2507.11710/) (2025)
- [Peeling Context from Cause for Molecular Property Prediction](https://mlsanity.com/paper/2511.06692/) (2025)
- [Spiking Graph Predictive Coding for Reliable OOD Generalization](https://mlsanity.com/paper/2602.19392/) (2026)
- [Causal Direct Preference Optimization for Distributionally Robust Generative Recommendation](https://mlsanity.com/paper/2603.22335/) (2026)
- [CGRL: Causal-Guided Representation Learning for Node-Level Out-of-Distribution Generalization](https://mlsanity.com/paper/2603.24304/) (2026)
- [A Closer Look at the Application of Causal Inference in Graph Representation Learning](https://mlsanity.com/paper/2604.08890/) (2026)
- [Rethinking Generalization in Graph Neural Networks: A Structural Complexity Perspective](https://mlsanity.com/paper/2605.13597/) (2026)
- [Transportable Causal Effect Estimation across Networks under Interference](https://mlsanity.com/paper/2608.18932/) (2026)
- [CATeye: Coupled Attribute-Topology Invariance Learning for Voucher Abuse Detection](https://mlsanity.com/paper/2609.01425/) (2026)

## Abstract (arXiv)

Out-of-distribution (OOD) generalization has gained increasing attentions for learning on graphs, as graph neural networks (GNNs) often exhibit performance degradation with distribution shifts. The challenge is that distribution shifts on graphs involve intricate interconnections between nodes, and the environment labels are often absent in data. In this paper, we adopt a bottom-up data-generative perspective and reveal a key observation through causal analysis: the crux of GNNs' failure in OOD generalization lies in the latent confounding bias from the environment. The latter misguides the model to leverage environment-sensitive correlations between ego-graph features and target nodes' labels, resulting in undesirable generalization on new unseen nodes. Built upon this analysis, we introduce a conceptually simple yet principled approach for training robust GNNs under node-level distribution shifts, without prior knowledge of environment labels. Our method resorts to a new learning objective derived from causal inference that coordinates an environment estimator and a mixture-of-expert GNN predictor. The new approach can counteract the confounding bias in training data and facilitate learning generalizable predictive relations. Extensive experiment demonstrates that our model can effectively enhance generalization with various types of distribution shifts and yield up to 27.4% accuracy improvement over state-of-the-arts on graph OOD generalization benchmarks. Source codes are available at https://github.com/fannie1208/CaNet.