mlsanityData to 14 Oct 2026

Active Learning for Graph Neural Networks via Node Feature Propagation

arXiv 1910.07567 ↗First posted 16 Oct 2019cs.LG stat.MLcited by 37

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) for prediction tasks like node classification or edge prediction have received increasing attention in recent machine learning from graphically structured data. However, a large quantity of labeled graphs is difficult to obtain, which significantly limits the true success of GNNs. Although active learning has been widely studied for addressing label-sparse issues with other data types like text, images, etc., how to make it effective over graphs is an open question for research. In this paper, we present an investigation on active learning with GNNs for node classification tasks. Specifically, we propose a new method, which uses node feature propagation followed by K-Medoids clustering of the nodes for instance selection in active learning. With a theoretical bound analysis we justify the design choice of our approach. In our experiments on four benchmark datasets, the proposed method outperforms other representative baseline methods consistently and significantly.

Key facts. Cited by 37 papers in the map (data through 14 Oct 2026). First posted on arXiv 16 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 5; 2023: 10; 2024: 11; 2025: 3; 2026: 4.

37 papers.

Sort:

By area:

  1. 2023Exploring the Potential of Large Language Models (LLMs) in Learning on Graphscited by 274
  2. 2023Label-free Node Classification on Graphs with Large Language Models (LLMS)cited by 72
  3. 2023CHATREPORT: Democratizing Sustainability Disclosure Analysis through LLM-based Toolscited by 29
  4. 2021Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximizationcited by 28
  5. 2023Data-centric Graph Learning: A Surveycited by 22
  6. 2023Towards Data-centric Graph Machine Learning: Review and Outlookcited by 15
  7. 2022Partition-Based Active Learning for Graph Neural Networkscited by 12
  8. 2024Uncertainty for Active Learning on Graphscited by 12
  9. 2024LEGO-Learn: Label-Efficient Graph Open-Set Learningcited by 10
  10. 2021Interscript: A dataset for interactive learning of scripts through error feedbackcited by 9
  11. 2024FastGAS: Fast Graph-based Annotation Selection for In-Context Learningcited by 8
  12. 2024Multitask Active Learning for Graph Anomaly Detectioncited by 7
25 more
  1. 2021CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentationcited by 6
  2. 2024Leveraging Large Language Models for Effective Label-free Node Classification in Text-Attributed Graphscited by 6
  3. 2025Few-Shot Graph Out-of-Distribution Detection with LLMscited by 6
  4. 2021Improving Neural Model Performance through Natural Language Feedback on Their Explanationscited by 5
  5. 2023A Unified Active Learning Framework for Annotating Graph Data with Application to Software Source Code Performance Predictioncited by 4
  6. 2022SMARTQUERY: An Active Learning Framework for Graph Neural Networks through Hybrid Uncertainty Reductioncited by 3
  7. 2022Dissimilar Nodes Improve Graph Active Learningcited by 3
  8. 2023Mitigating Semantic Confusion from Hostile Neighborhood for Graph Active Learningcited by 3
  9. 2024On the Topology Awareness and Generalization Performance of Graph Neural Networkscited by 3
  10. 2024Uplift Modeling Under Limited Supervisioncited by 3
  11. 2024Test-Time Training on Graphs with Large Language Models (LLMs)cited by 3
  12. 2024Enhancing Graph Neural Networks with Limited Labeled Data by Actively Distilling Knowledge from Large Language Modelscited by 3
  13. 2022Tackling Provably Hard Representative Selection via Graph Neural Networkscited by 2
  14. 2022ScatterSample: Diversified Label Sampling for Data Efficient Graph Neural Network Learningcited by 1
  15. 2023DiffusAL: Coupling Active Learning with Graph Diffusion for Label-Efficient Node Classificationcited by 1
  16. 2023CueGCL: Cluster-aware Personalized Self-Training for Unsupervised Graph Contrastive Learningcited by 1
  17. 2023A Structural-Clustering Based Active Learning for Graph Neural Networkscited by 1
  18. 2024Active Learning for Graphs with Noisy Structurescited by 1
  19. 2024Class-Balanced and Reinforced Active Learning on Graphscited by 1
  20. 2026LoGIC: Budgeted Context Construction for Node-Level Graph In-Context Learning with Tabular Foundation Modelscited by 1
  21. 2025Active Few-Shot Learning for Vertex Classification Starting from an Unlabeled Datasetcited by 0
  22. 2025GRAIL: A Benchmark for GRaph ActIve Learning in Dynamic Sensing Environmentscited by 0
  23. 2026Are Candidate Models Really Needed for Active Learning?cited by 0
  24. 2026Where LLM Annotators Fail: Label-Free Learning on Graphs with LLMscited by 0
  25. 2026ALINC: Active Learning for Inductive Node Classification via Graph Samplingcited by 0