# ROGPL: Robust Open-Set Graph Learning via Region-Based Prototype Learning

arXiv: https://arxiv.org/abs/2402.18495 · HTML: https://mlsanity.com/paper/2402.18495/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 41 references that are in the map.
- First posted on arXiv 28 Feb 2024.

## Builds on (most cited first, 26 of 26)

- [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)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [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)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [GMAN: A Graph Multi-Attention Network for Traffic Prediction](https://mlsanity.com/paper/1911.08415/) (2019)
- [Label Propagation for Deep Semi-supervised Learning](https://mlsanity.com/paper/1904.04717/) (2019)
- [Graph Self-Supervised Learning: A Survey](https://mlsanity.com/paper/2103.00111/) (2021)
- [WebVision Database: Visual Learning and Understanding from Web Data](https://mlsanity.com/paper/1708.02862/) (2017)
- [Learning from Noisy Labels with Distillation](https://mlsanity.com/paper/1703.02391/) (2017)
- [Robust Classification with Convolutional Prototype Learning](https://mlsanity.com/paper/1805.03438/) (2018)
- [Learning with Biased Complementary Labels](https://mlsanity.com/paper/1711.09535/) (2017)
- [NGC: A Unified Framework for Learning with Open-World Noisy Data](https://mlsanity.com/paper/2108.11035/) (2021)
- [Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations](https://mlsanity.com/paper/1611.05113/) (2016)
- [Mining on Manifolds: Metric Learning without Labels](https://mlsanity.com/paper/1803.11095/) (2018)
- [Graph Auto-Encoder Via Neighborhood Wasserstein Reconstruction](https://mlsanity.com/paper/2202.09025/) (2022)
- [Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs](https://mlsanity.com/paper/1603.08358/) (2016)
- [Open-Category Classification by Adversarial Sample Generation](https://mlsanity.com/paper/1705.08722/) (2017)
- [Robust Graph Representation Learning for Local Corruption Recovery](https://mlsanity.com/paper/2202.04936/) (2022)
- [Shift-Robust Node Classification via Graph Adversarial Clustering](https://mlsanity.com/paper/2203.15802/) (2022)
- [G2Pxy: Generative Open-Set Node Classification on Graphs with Proxy Unknowns](https://mlsanity.com/paper/2308.05463/) (2023)
- [ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection](https://mlsanity.com/paper/2108.12229/) (2021)
- [Denoising Multi-Similarity Formulation: A Self-paced Curriculum-Driven Approach for Robust Metric Learning](https://mlsanity.com/paper/2211.11751/) (2022)

## Built on by (most cited first, 2 of 2)

- [OOVDet: Low-Density Prior Learning for Zero-Shot Out-of-Vocabulary Object Detection](https://mlsanity.com/paper/2601.22685/) (2026)
- [HOPE: Heterophily-Aware Open-Set Node Classification with Pseudo-Extrapolation](https://mlsanity.com/paper/2609.08685/) (2026)

## Abstract (arXiv)

Open-set graph learning is a practical task that aims to classify the known class nodes and to identify unknown class samples as unknowns. Conventional node classification methods usually perform unsatisfactorily in open-set scenarios due to the complex data they encounter, such as out-of-distribution (OOD) data and in-distribution (IND) noise. OOD data are samples that do not belong to any known classes. They are outliers if they occur in training (OOD noise), and open-set samples if they occur in testing. IND noise are training samples which are assigned incorrect labels. The existence of IND noise and OOD noise is prevalent, which usually cause the ambiguity problem, including the intra-class variety problem and the inter-class confusion problem. Thus, to explore robust open-set learning methods is necessary and difficult, and it becomes even more difficult for non-IID graph data.To this end, we propose a unified framework named ROGPL to achieve robust open-set learning on complex noisy graph data, by introducing prototype learning. In specific, ROGPL consists of two modules, i.e., denoising via label propagation and open-set prototype learning via regions. The first module corrects noisy labels through similarity-based label propagation and removes low-confidence samples, to solve the intra-class variety problem caused by noise. The second module learns open-set prototypes for each known class via non-overlapped regions and remains both interior and border prototypes to remedy the inter-class confusion problem.The two modules are iteratively updated under the constraints of classification loss and prototype diversity loss. To the best of our knowledge, the proposed ROGPL is the first robust open-set node classification method for graph data with complex noise.