# Shift-Robust Node Classification via Graph Adversarial Clustering

arXiv: https://arxiv.org/abs/2203.15802 · HTML: https://mlsanity.com/paper/2203.15802/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 42 references that are in the map.
- First posted on arXiv 7 Mar 2022.

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Deep Transfer Learning with Joint Adaptation Networks](https://mlsanity.com/paper/1605.06636/) (2016)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks](https://mlsanity.com/paper/1909.01315/) (2019)
- [Generalization and Representational Limits of Graph Neural Networks](https://mlsanity.com/paper/2002.06157/) (2020)
- [Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning](https://mlsanity.com/paper/1702.08811/) (2017)
- [Graph Clustering with Graph Neural Networks](https://mlsanity.com/paper/2006.16904/) (2020)
- [DOC: Deep Open Classification of Text Documents](https://mlsanity.com/paper/1709.08716/) (2017)
- [Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data](https://mlsanity.com/paper/2108.01099/) (2021)
- [Stability and Generalization of Graph Convolutional Neural Networks](https://mlsanity.com/paper/1905.01004/) (2019)
- [Subgroup Generalization and Fairness of Graph Neural Networks](https://mlsanity.com/paper/2106.15535/) (2021)
- [Progressive Graph Learning for Open-Set Domain Adaptation](https://mlsanity.com/paper/2006.12087/) (2020)

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

- [Pairwise Alignment Improves Graph Domain Adaptation](https://mlsanity.com/paper/2403.01092/) (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)
- [Beyond Generalization: A Survey of Out-Of-Distribution Adaptation on Graphs](https://mlsanity.com/paper/2402.11153/) (2024)
- [G2Pxy: Generative Open-Set Node Classification on Graphs with Proxy Unknowns](https://mlsanity.com/paper/2308.05463/) (2023)
- [ROGPL: Robust Open-Set Graph Learning via Region-Based Prototype Learning](https://mlsanity.com/paper/2402.18495/) (2024)

## Abstract (arXiv)

Graph Neural Networks (GNNs) are de facto node classification models in graph structured data. However, during testing-time, these algorithms assume no data shift, i.e., Prtrain(X,Y) = Prtest(X,Y). Domain adaption methods can be adopted for data shift, yet most of them are designed to only encourage similar feature distribution between source and target data. Conditional shift on classes can still affect such adaption. Fortunately, graph yields graph homophily across different data distributions. In response, we propose Shift-Robust Node Classification (SRNC) to address these limitations. We introduce an unsupervised cluster GNN on target graph to group the similar nodes by graph homophily. An adversarial loss with label information on source graph is used upon clustering objective. Then a shift-robust classifier is optimized on training graph and adversarial samples on target graph, which are generated by cluster GNN. We conduct experiments on both open-set shift and representation-shift, which demonstrates the superior accuracy of SRNC on generalizing to test graph with data shift. SRNC is consistently better than previous SoTA domain adaption algorithm on graph that progressively use model predictions on target graph for training.