# When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty

arXiv: https://arxiv.org/abs/2505.13989 · HTML: https://mlsanity.com/paper/2505.13989/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 48 references that are in the map.
- First posted on arXiv 20 May 2025.

## Builds on (most cited first, 30 of 37)

- [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)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Uncertainty Aware Semi-Supervised Learning on Graph Data](https://mlsanity.com/paper/2010.12783/) (2020)
- [Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification](https://mlsanity.com/paper/2110.14012/) (2021)
- [Label-free Node Classification on Graphs with Large Language Models (LLMS)](https://mlsanity.com/paper/2310.04668/) (2023)
- [Energy-based Out-of-Distribution Detection for Graph Neural Networks](https://mlsanity.com/paper/2302.02914/) (2023)
- [Streaming Graph Neural Networks via Continual Learning](https://mlsanity.com/paper/2009.10951/) (2020)
- [Augmenting Low-Resource Text Classification with Graph-Grounded Pre-training and Prompting](https://mlsanity.com/paper/2305.03324/) (2023)
- [SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptation](https://mlsanity.com/paper/2502.05424/) (2025)
- [GOFA: A Generative One-For-All Model for Joint Graph Language Modeling](https://mlsanity.com/paper/2407.09709/) (2024)
- [ARC: A Generalist Graph Anomaly Detector with In-Context Learning](https://mlsanity.com/paper/2405.16771/) (2024)
- [GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection](https://mlsanity.com/paper/2211.04208/) (2022)
- [Continual Learning of Knowledge Graph Embeddings](https://mlsanity.com/paper/2101.05850/) (2021)
- [Learning on Graphs with Out-of-Distribution Nodes](https://mlsanity.com/paper/2308.06714/) (2023)
- [Hierarchical Prototype Networks for Continual Graph Representation Learning](https://mlsanity.com/paper/2111.15422/) (2021)
- [Disentangle-based Continual Graph Representation Learning](https://mlsanity.com/paper/2010.02565/) (2020)
- [Graph-Based Continual Learning](https://mlsanity.com/paper/2007.04813/) (2020)
- [Reinforced Continual Learning for Graphs](https://mlsanity.com/paper/2209.01556/) (2022)
- [Lifelong Learning of Graph Neural Networks for Open-World Node Classification](https://mlsanity.com/paper/2006.14422/) (2020)
- [Entropic Out-of-Distribution Detection](https://mlsanity.com/paper/1908.05569/) (2019)
- [Motif Prediction with Graph Neural Networks](https://mlsanity.com/paper/2106.00761/) (2021)
- [Open-world Semi-supervised Novel Class Discovery](https://mlsanity.com/paper/2305.13095/) (2023)
- [GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generation](https://mlsanity.com/paper/2502.05780/) (2025)
- [DSLR: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual Learning](https://mlsanity.com/paper/2402.13711/) (2024)
- [LEGO-Learn: Label-Efficient Graph Open-Set Learning](https://mlsanity.com/paper/2410.16386/) (2024)
- [Universal Graph Continual Learning](https://mlsanity.com/paper/2308.13982/) (2023)
- [Graph Continual Learning with Debiased Lossless Memory Replay](https://mlsanity.com/paper/2404.10984/) (2024)
- [Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphs](https://mlsanity.com/paper/2502.17912/) (2025)

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

- [MOVE: Multimodal Open-world Verification and Expansion for Graph Learning](https://mlsanity.com/paper/2610.00268/) (2026)

## Abstract (arXiv)

Recently, large language models (LLMs) have significantly advanced text-attributed graph (TAG) learning. However, existing methods inadequately handle data uncertainty in open-world scenarios, especially concerning limited labeling and unknown-class nodes. Prior solutions typically rely on isolated semantic or structural approaches for unknown-class rejection, lacking effective annotation pipelines. To address these limitations, we propose Open-world Graph Assistant (OGA), an LLM-based framework that combines adaptive label traceability, which integrates semantics and topology for unknown-class rejection, and a graph label annotator to enable model updates using newly annotated nodes. Comprehensive experiments demonstrate OGA's effectiveness and practicality.