# Beyond the Known: Novel Class Discovery for Open-world Graph Learning

arXiv: https://arxiv.org/abs/2403.19907 · HTML: https://mlsanity.com/paper/2403.19907/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 36 references that are in the map.
- First posted on arXiv 29 Mar 2024.

## Builds on (most cited first, 24 of 24)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Spectral Networks and Locally Connected Networks on Graphs](https://mlsanity.com/paper/1312.6203/) (2013)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Graph Contrastive Learning with Adaptive Augmentation](https://mlsanity.com/paper/2010.14945/) (2020)
- [Learning Convolutional Neural Networks for Graphs](https://mlsanity.com/paper/1605.05273/) (2016)
- [Recent Advances in Open Set Recognition: A Survey](https://mlsanity.com/paper/1811.08581/) (2018)
- [Learning to Discover Novel Visual Categories via Deep Transfer Clustering](https://mlsanity.com/paper/1908.09884/) (2019)
- [Generalized Category Discovery](https://mlsanity.com/paper/2201.02609/) (2022)
- [Adaptive Sampling Towards Fast Graph Representation Learning](https://mlsanity.com/paper/1809.05343/) (2018)
- [Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning](https://mlsanity.com/paper/2103.00113/) (2021)
- [Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2102.03526/) (2021)
- [Learning to cluster in order to transfer across domains and tasks](https://mlsanity.com/paper/1711.10125/) (2017)
- [Parametric Classification for Generalized Category Discovery: A Baseline Study](https://mlsanity.com/paper/2211.11727/) (2022)
- [Conditional Gaussian Distribution Learning for Open Set Recognition](https://mlsanity.com/paper/2003.08823/) (2020)
- [OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open World](https://mlsanity.com/paper/2004.05551/) (2020)
- [Graph Prototypical Networks for Few-shot Learning on Attributed Networks](https://mlsanity.com/paper/2006.12739/) (2020)
- [Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discovery](https://mlsanity.com/paper/2305.06144/) (2023)
- [Convolutional Kernel Networks for Graph-Structured Data](https://mlsanity.com/paper/2003.05189/) (2020)
- [Optimization of Graph Neural Networks with Natural Gradient Descent](https://mlsanity.com/paper/2008.09624/) (2020)
- [Geometer: Graph Few-Shot Class-Incremental Learning via Prototype Representation](https://mlsanity.com/paper/2205.13954/) (2022)
- [Graph Partition Neural Networks for Semi-Supervised Classification](https://mlsanity.com/paper/1803.06272/) (2018)
- [Open-world Semi-supervised Novel Class Discovery](https://mlsanity.com/paper/2305.13095/) (2023)

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

- [When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty](https://mlsanity.com/paper/2505.13989/) (2025)
- [Information Theory in Open-world Machine Learning Foundations, Frameworks, and Future Direction](https://mlsanity.com/paper/2510.15422/) (2025)

## Abstract (arXiv)

Node classification on graphs is of great importance in many applications. Due to the limited labeling capability and evolution in real-world open scenarios, novel classes can emerge on unlabeled testing nodes. However, little attention has been paid to novel class discovery on graphs. Discovering novel classes is challenging as novel and known class nodes are correlated by edges, which makes their representations indistinguishable when applying message passing GNNs. Furthermore, the novel classes lack labeling information to guide the learning process. In this paper, we propose a novel method Open-world gRAph neuraL network (ORAL) to tackle these challenges. ORAL first detects correlations between classes through semi-supervised prototypical learning. Inter-class correlations are subsequently eliminated by the prototypical attention network, leading to distinctive representations for different classes. Furthermore, to fully explore multi-scale graph features for alleviating label deficiencies, ORAL generates pseudo-labels by aligning and ensembling label estimations from multiple stacked prototypical attention networks. Extensive experiments on several benchmark datasets show the effectiveness of our proposed method.