# Dissecting the Failure of Invariant Learning on Graphs

arXiv: https://arxiv.org/abs/2411.02847 · HTML: https://mlsanity.com/paper/2411.02847/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 57 references that are in the map.
- First posted on arXiv 5 Nov 2024.

## Builds on (most cited first, 12 of 12)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Gradient Matching for Domain Generalization](https://mlsanity.com/paper/2104.09937/) (2021)
- [Discovering Invariant Rationales for Graph Neural Networks](https://mlsanity.com/paper/2201.12872/) (2022)
- [Empowering Graph Representation Learning with Test-Time Graph Transformation](https://mlsanity.com/paper/2210.03561/) (2022)
- [Graph Out-of-Distribution Generalization via Causal Intervention](https://mlsanity.com/paper/2402.11494/) (2024)
- [Spurious Feature Diversification Improves Out-of-distribution Generalization](https://mlsanity.com/paper/2309.17230/) (2023)
- [Graph Invariant Learning with Subgraph Co-mixup for Out-Of-Distribution Generalization](https://mlsanity.com/paper/2312.10988/) (2023)
- [Graph Structure and Feature Extrapolation for Out-of-Distribution Generalization](https://mlsanity.com/paper/2306.08076/) (2023)
- [Stable Prediction on Graphs with Agnostic Distribution Shift](https://mlsanity.com/paper/2110.03865/) (2021)
- [Unifying Invariance and Spuriousity for Graph Out-of-Distribution via Probability of Necessity and Sufficiency](https://mlsanity.com/paper/2402.09165/) (2024)
- [Graphs Generalization under Distribution Shifts](https://mlsanity.com/paper/2403.16334/) (2024)

## Built on by (most cited first, 5 of 5)

- [SA2GFM: Enhancing Robust Graph Foundation Models with Structure-Aware Semantic Augmentation](https://mlsanity.com/paper/2512.07857/) (2025)
- [GraphIFE: Rethinking Graph Imbalance Node Classification via Invariant Learning](https://mlsanity.com/paper/2509.23616/) (2025)
- [Peeling Context from Cause for Molecular Property Prediction](https://mlsanity.com/paper/2511.06692/) (2025)
- [CGRL: Causal-Guided Representation Learning for Node-Level Out-of-Distribution Generalization](https://mlsanity.com/paper/2603.24304/) (2026)
- [Beyond Site Agreement: Re-estimation for Brain Network Generalization](https://mlsanity.com/paper/2609.34611/) (2026)

## Abstract (arXiv)

Enhancing node-level Out-Of-Distribution (OOD) generalization on graphs remains a crucial area of research. In this paper, we develop a Structural Causal Model (SCM) to theoretically dissect the performance of two prominent invariant learning methods -- Invariant Risk Minimization (IRM) and Variance-Risk Extrapolation (VREx) -- in node-level OOD settings. Our analysis reveals a critical limitation: due to the lack of class-conditional invariance constraints, these methods may struggle to accurately identify the structure of the predictive invariant ego-graph and consequently rely on spurious features. To address this, we propose Cross-environment Intra-class Alignment (CIA), which explicitly eliminates spurious features by aligning cross-environment representations conditioned on the same class, bypassing the need for explicit knowledge of the causal pattern structure. To adapt CIA to node-level OOD scenarios where environment labels are hard to obtain, we further propose CIA-LRA (Localized Reweighting Alignment) that leverages the distribution of neighboring labels to selectively align node representations, effectively distinguishing and preserving invariant features while removing spurious ones, all without relying on environment labels. We theoretically prove CIA-LRA's effectiveness by deriving an OOD generalization error bound based on PAC-Bayesian analysis. Experiments on graph OOD benchmarks validate the superiority of CIA and CIA-LRA, marking a significant advancement in node-level OOD generalization. The codes are available at https://github.com/NOVAglow646/NeurIPS24-Invariant-Learning-on-Graphs.