# Mind the Label Shift of Augmentation-based Graph OOD Generalization

arXiv: https://arxiv.org/abs/2303.14859 · HTML: https://mlsanity.com/paper/2303.14859/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 52 of its 68 references that are in the map.
- First posted on arXiv 27 Mar 2023.

## Builds on (most cited first, 30 of 52)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [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)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [Multi-scale Attributed Node Embedding](https://mlsanity.com/paper/1909.13021/) (2019)
- [Causal inference using invariant prediction: identification and confidence intervals](https://mlsanity.com/paper/1501.01332/) (2015)
- [Graph Neural Networks in Recommender Systems: A Survey](https://mlsanity.com/paper/2011.02260/) (2020)
- [Graph U-Nets](https://mlsanity.com/paper/1905.05178/) (2019)
- [Generalizing to Unseen Domains via Adversarial Data Augmentation](https://mlsanity.com/paper/1805.12018/) (2018)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One](https://mlsanity.com/paper/1912.03263/) (2019)
- [Graph Structure Learning for Robust Graph Neural Networks](https://mlsanity.com/paper/2005.10203/) (2020)
- [Certifying Some Distributional Robustness with Principled Adversarial Training](https://mlsanity.com/paper/1710.10571/) (2017)
- [Environment Inference for Invariant Learning](https://mlsanity.com/paper/2010.07249/) (2020)
- [Concrete Dropout](https://mlsanity.com/paper/1705.07832/) (2017)
- [Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization](https://mlsanity.com/paper/2106.06607/) (2021)
- [Discovering Invariant Rationales for Graph Neural Networks](https://mlsanity.com/paper/2201.12872/) (2022)

## Built on by (most cited first, 30 of 34)

- [A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challenges](https://mlsanity.com/paper/2403.04468/) (2024)
- [Does Invariant Graph Learning via Environment Augmentation Learn Invariance?](https://mlsanity.com/paper/2310.19035/) (2023)
- [Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning](https://mlsanity.com/paper/2505.11953/) (2025)
- [Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization](https://mlsanity.com/paper/2311.11114/) (2023)
- [Subgraph Pooling: Tackling Negative Transfer on Graphs](https://mlsanity.com/paper/2402.08907/) (2024)
- [A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptation](https://mlsanity.com/paper/2410.19265/) (2024)
- [GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generation](https://mlsanity.com/paper/2502.05780/) (2025)
- [Handling Out-of-Distribution Data: A Survey](https://mlsanity.com/paper/2507.21160/) (2025)
- [Investigating Out-of-Distribution Generalization of GNNs: An Architecture Perspective](https://mlsanity.com/paper/2402.08228/) (2024)
- [How Interpretable Are Interpretable Graph Neural Networks?](https://mlsanity.com/paper/2406.07955/) (2024)
- [Safety in Graph Machine Learning: Threats and Safeguards](https://mlsanity.com/paper/2405.11034/) (2024)
- [Graph Structure and Feature Extrapolation for Out-of-Distribution Generalization](https://mlsanity.com/paper/2306.08076/) (2023)
- [Graph Out-of-Distribution Generalization with Controllable Data Augmentation](https://mlsanity.com/paper/2308.08344/) (2023)
- [Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?](https://mlsanity.com/paper/2510.16582/) (2025)
- [Improving out-of-distribution generalization in graphs via hierarchical semantic environments](https://mlsanity.com/paper/2403.01773/) (2024)
- [Rumor Detection with Diverse Counterfactual Evidence](https://mlsanity.com/paper/2307.09296/) (2023)
- [When Graph Neural Network Meets Causality: Opportunities, Methodologies and An Outlook](https://mlsanity.com/paper/2312.12477/) (2023)
- [Subgraph Aggregation for Out-of-Distribution Generalization on Graphs](https://mlsanity.com/paper/2410.22228/) (2024)
- [Learning to Group Auxiliary Datasets for Molecule](https://mlsanity.com/paper/2307.04052/) (2023)
- [Topology-Aware Dynamic Reweighting for Distribution Shifts on Graph](https://mlsanity.com/paper/2406.01066/) (2024)
- [Pruning Spurious Subgraphs for Graph Out-of-Distribution Generalization](https://mlsanity.com/paper/2506.05957/) (2025)
- [Addressing the Impact of Localized Training Data in Graph Neural Networks](https://mlsanity.com/paper/2307.12689/) (2023)
- [Enhancing Distribution and Label Consistency for Graph Out-of-Distribution Generalization](https://mlsanity.com/paper/2501.04102/) (2025)
- [Generative Risk Minimization for Out-of-Distribution Generalization on Graphs](https://mlsanity.com/paper/2502.07968/) (2025)
- [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)
- [Context-aware Graph Causality Inference for Few-Shot Molecular Property Prediction](https://mlsanity.com/paper/2601.11135/) (2026)
- [From Subtle to Significant: Prompt-Driven Self-Improving Optimization in Test-Time Graph OOD Detection](https://mlsanity.com/paper/2602.17342/) (2026)
- [IENE: Identifying and Extrapolating the Node Environment for Out-of-Distribution Generalization on Graphs](https://mlsanity.com/paper/2406.00764/) (2024)
- [Core Knowledge Learning Framework for Graph Adaptation and Scalability Learning](https://mlsanity.com/paper/2407.01886/) (2024)

## Abstract (arXiv)

Out-of-distribution (OOD) generalization is an important issue for Graph Neural Networks (GNNs). Recent works employ different graph editions to generate augmented environments and learn an invariant GNN for generalization. However, the label shift usually occurs in augmentation since graph structural edition inevitably alters the graph label. This brings inconsistent predictive relationships among augmented environments, which is harmful to generalization. To address this issue, we propose LiSA, which generates label-invariant augmentations to facilitate graph OOD generalization. Instead of resorting to graph editions, LiSA exploits Label-invariant Subgraphs of the training graphs to construct Augmented environments. Specifically, LiSA first designs the variational subgraph generators to extract locally predictive patterns and construct multiple label-invariant subgraphs efficiently. Then, the subgraphs produced by different generators are collected to build different augmented environments. To promote diversity among augmented environments, LiSA further introduces a tractable energy-based regularization to enlarge pair-wise distances between the distributions of environments. In this manner, LiSA generates diverse augmented environments with a consistent predictive relationship and facilitates learning an invariant GNN. Extensive experiments on node-level and graph-level OOD benchmarks show that LiSA achieves impressive generalization performance with different GNN backbones. Code is available on urlhttps://github.com/Samyu0304/LiSA.