# SCL-GNN: Towards Generalizable Graph Neural Networks via Spurious Correlation Learning

arXiv: https://arxiv.org/abs/2603.08270 · HTML: https://mlsanity.com/paper/2603.08270/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 42 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Builds on (most cited first, 28 of 28)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Multi-Task Learning as Multi-Objective Optimization](https://mlsanity.com/paper/1810.04650/) (2018)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [Self-Supervised Learning of Graph Neural Networks: A Unified Review](https://mlsanity.com/paper/2102.10757/) (2021)
- [Handling Distribution Shifts on Graphs: An Invariance Perspective](https://mlsanity.com/paper/2202.02466/) (2022)
- [On Feature Learning in the Presence of Spurious Correlations](https://mlsanity.com/paper/2210.11369/) (2022)
- [Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs](https://mlsanity.com/paper/2202.05441/) (2022)
- [Contextual Stochastic Block Models](https://mlsanity.com/paper/1807.09596/) (2018)
- [Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data](https://mlsanity.com/paper/2108.01099/) (2021)
- [Molecular graph generation with Graph Neural Networks](https://mlsanity.com/paper/2012.07397/) (2020)
- [OOD-GNN: Out-of-Distribution Generalized Graph Neural Network](https://mlsanity.com/paper/2112.03806/) (2021)
- [Generalizing Graph Neural Networks on Out-Of-Distribution Graphs](https://mlsanity.com/paper/2111.10657/) (2021)
- [On the Impact of Spurious Correlation for Out-of-distribution Detection](https://mlsanity.com/paper/2109.05642/) (2021)
- [Stable Prediction with Model Misspecification and Agnostic Distribution Shift](https://mlsanity.com/paper/2001.11713/) (2020)
- [ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Prediction](https://mlsanity.com/paper/2007.03196/) (2020)
- [Towards Understanding the Generalization of Graph Neural Networks](https://mlsanity.com/paper/2305.08048/) (2023)
- [Are Vision Transformers Robust to Spurious Correlations?](https://mlsanity.com/paper/2203.09125/) (2022)
- [Graph Out-of-Distribution Generalization via Causal Intervention](https://mlsanity.com/paper/2402.11494/) (2024)
- [Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization](https://mlsanity.com/paper/2306.01103/) (2023)
- [Spuriosity Didn't Kill the Classifier: Using Invariant Predictions to Harness Spurious Features](https://mlsanity.com/paper/2307.09933/) (2023)
- [Robustness to Spurious Correlations Improves Semantic Out-of-Distribution Detection](https://mlsanity.com/paper/2302.04132/) (2023)
- [Learning Divergence Fields for Shift-Robust Graph Representations](https://mlsanity.com/paper/2406.04963/) (2024)

## Built on by (most cited first, 1 of 1)

- [Disentangling Homophily and Rarity: Explaining Failure in Graph Neural Networks](https://mlsanity.com/paper/2608.14823/) (2026)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have demonstrated remarkable success across diverse tasks. However, their generalization capability is often hindered by spurious correlations between node features and labels in the graph. Our analysis reveals that GNNs tend to exploit imperceptible statistical correlations in training data, even when such correlations are unreliable for prediction. To address this challenge, we propose the Spurious Correlation Learning Graph Neural Network (SCL-GNN), a novel framework designed to enhance generalization on both Independent and Identically Distributed (IID) and Out-of-Distribution (OOD) graphs. SCL-GNN incorporates a principled spurious correlation learning mechanism, leveraging the Hilbert-Schmidt Independence Criterion (HSIC) to quantify correlations between node representations and class scores. This enables the model to identify and mitigate irrelevant but influential spurious correlations effectively. Additionally, we introduce an efficient bi-level optimization strategy to jointly optimize modules and GNN parameters, preventing overfitting. Extensive experiments on real-world and synthetic datasets demonstrate that SCL-GNN consistently outperforms state-of-the-art baselines under various distribution shifts, highlighting its robustness and generalization capabilities.