mlsanityData to 14 Oct 2026

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

arXiv 2505.13989 ↗First posted 20 May 2025cs.LG cs.AIcited by 1

Not on the map. Why?

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.

Key facts. Cited by 1 paper 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

37 of 48 references.

References · 37

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2018How Powerful are Graph Neural Networks?cited by 4,393
  5. 2020Uncertainty Aware Semi-Supervised Learning on Graph Datacited by 95
  6. 2021Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classificationcited by 80
  7. 2023Label-free Node Classification on Graphs with Large Language Models (LLMS)cited by 72
  8. 2023Energy-based Out-of-Distribution Detection for Graph Neural Networkscited by 68
  9. 2020Streaming Graph Neural Networks via Continual Learningcited by 64
  10. 2023Augmenting Low-Resource Text Classification with Graph-Grounded Pre-training and Promptingcited by 62
  11. 2025SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptationcited by 62
  12. 2024GOFA: A Generative One-For-All Model for Joint Graph Language Modelingcited by 57
25 more
  1. 2024ARC: A Generalist Graph Anomaly Detector with In-Context Learningcited by 48
  2. 2022GOOD-D: On Unsupervised Graph Out-Of-Distribution Detectioncited by 47
  3. 2021Continual Learning of Knowledge Graph Embeddingscited by 35
  4. 2023Learning on Graphs with Out-of-Distribution Nodescited by 29
  5. 2021Hierarchical Prototype Networks for Continual Graph Representation Learningcited by 28
  6. 2020Disentangle-based Continual Graph Representation Learningcited by 25
  7. 2020Graph-Based Continual Learningcited by 24
  8. 2022Reinforced Continual Learning for Graphscited by 24
  9. 2020Lifelong Learning of Graph Neural Networks for Open-World Node Classificationcited by 22
  10. 2019Entropic Out-of-Distribution Detectioncited by 21
  11. 2021Motif Prediction with Graph Neural Networkscited by 18
  12. 2023Open-world Semi-supervised Novel Class Discoverycited by 15
  13. 2025GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generationcited by 15
  14. 2024DSLR: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual Learningcited by 14
  15. 2024LEGO-Learn: Label-Efficient Graph Open-Set Learningcited by 10
  16. 2023Universal Graph Continual Learningcited by 9
  17. 2024Graph Continual Learning with Debiased Lossless Memory Replaycited by 9
  18. 2025Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphscited by 9
  19. 2024Contrastive Augmented Graph2Graph Memory Interaction for Few Shot Continual Learningcited by 7
  20. 2025Bounded and Uniform Energy-based Out-of-distribution Detection for Graphscited by 6
  21. 2025Graph Synthetic Out-of-Distribution Exposure with Large Language Modelscited by 6
  22. 2023Open-World Lifelong Graph Learningcited by 5
  23. 2024FTF-ER: Feature-Topology Fusion-Based Experience Replay Method for Continual Graph Learningcited by 3
  24. 2024Beyond the Known: Novel Class Discovery for Open-world Graph Learningcited by 2
  25. 2024Open-World Semi-Supervised Learning for Node Classificationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026MOVE: Multimodal Open-world Verification and Expansion for Graph Learningcited by 0