mlsanityData to 13 Oct 2026

Graph Policy Network for Transferable Active Learning on Graphs

arXiv 2006.13463 ↗First posted 24 Jun 2020cs.LG cs.AI stat.MLcited by 50

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) have been attracting increasing popularity due to their simplicity and effectiveness in a variety of fields. However, a large number of labeled data is generally required to train these networks, which could be very expensive to obtain in some domains. In this paper, we study active learning for GNNs, i.e., how to efficiently label the nodes on a graph to reduce the annotation cost of training GNNs. We formulate the problem as a sequential decision process on graphs and train a GNN-based policy network with reinforcement learning to learn the optimal query strategy. By jointly training on several source graphs with full labels, we learn a transferable active learning policy which can directly generalize to unlabeled target graphs. Experimental results on multiple datasets from different domains prove the effectiveness of the learned policy in promoting active learning performance in both settings of transferring between graphs in the same domain and across different domains.

Key facts. Cited by 50 papers in the map (data through 13 Oct 2026). First posted on arXiv 24 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 5; 2022: 11; 2023: 10; 2024: 13; 2025: 6; 2026: 5.

50 papers.

Sort:

By area:

  1. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 163
  2. 2023Label-free Node Classification on Graphs with Large Language Models (LLMS)cited by 72
  3. 2024A Survey on Deep Active Learning: Recent Advances and New Frontierscited by 54
  4. 2021Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networkscited by 50
  5. 2021On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphscited by 49
  6. 2021RIM: Reliable Influence-based Active Learning on Graphscited by 23
  7. 2024Uncertainty in Graph Neural Networks: A Surveycited by 23
  8. 2025Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunitiescited by 23
  9. 2023Data-centric Graph Learning: A Surveycited by 22
  10. 2022Reinforcement learning on graphs: A surveycited by 18
  11. 2022MentorGNN: Deriving Curriculum for Pre-Training GNNscited by 18
  12. 2023Efficient Subgraph GNNs by Learning Effective Selection Policiescited by 17
38 more
  1. 2021Graph Neural Networks: Methods, Applications, and Opportunitiescited by 16
  2. 2022Information Gain Propagation: a new way to Graph Active Learning with Soft Labelscited by 16
  3. 2022JuryGCN: Quantifying Jackknife Uncertainty on Graph Convolutional Networkscited by 15
  4. 2023Towards Data-centric Graph Machine Learning: Review and Outlookcited by 15
  5. 2022Partition-Based Active Learning for Graph Neural Networkscited by 12
  6. 2024Uncertainty for Active Learning on Graphscited by 12
  7. 2023MAG-GNN: Reinforcement Learning Boosted Graph Neural Networkcited by 11
  8. 2024LEGO-Learn: Label-Efficient Graph Open-Set Learningcited by 10
  9. 2024RELIEF: Reinforcement Learning Empowered Graph Feature Prompt Tuningcited by 9
  10. 2023EvoluNet: Advancing Dynamic Non-IID Transfer Learning on Graphscited by 7
  11. 2022Reinforcement Learning Based Query Vertex Ordering Model for Subgraph Matchingcited by 6
  12. 2022Poisson Reweighted Laplacian Uncertainty Sampling for Graph-based Active Learningcited by 6
  13. 2024Graph-Skeleton: ~1% Nodes are Sufficient to Represent Billion-Scale Graphcited by 6
  14. 2025Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centralitycited by 5
  15. 2023StriderNET: A Graph Reinforcement Learning Approach to Optimize Atomic Structures on Rough Energy Landscapescited by 4
  16. 2023A Unified Active Learning Framework for Annotating Graph Data with Application to Software Source Code Performance Predictioncited by 4
  17. 2022SMARTQUERY: An Active Learning Framework for Graph Neural Networks through Hybrid Uncertainty Reductioncited by 3
  18. 2022Dissimilar Nodes Improve Graph Active Learningcited by 3
  19. 2023Generative Flow Networks for Precise Reward-Oriented Active Learning on Graphscited by 3
  20. 2023Towards Label Position Bias in Graph Neural Networkscited by 3
  21. 2024On the Topology Awareness and Generalization Performance of Graph Neural Networkscited by 3
  22. 2024Enhancing Graph Neural Networks with Limited Labeled Data by Actively Distilling Knowledge from Large Language Modelscited by 3
  23. 2025Learning and Editing Universal Graph Prompt Tuning via Reinforcement Learningcited by 3
  24. 2024Amortized nonmyopic active search via deep imitation learningcited by 2
  25. 2024DELTA: Dual Consistency Delving with Topological Uncertainty for Active Graph Domain Adaptationcited by 2
  26. 2025Language Models as Messengers: Enhancing Message Passing in Heterophilic Graph Learningcited by 2
  27. 2022Augmenting Knowledge Transfer across Graphscited by 1
  28. 2024Active Learning for Graphs with Noisy Structurescited by 1
  29. 2024Class-Balanced and Reinforced Active Learning on Graphscited by 1
  30. 2025Shapley-Guided Utility Learning for Effective Graph Inference Data Valuationcited by 1
  31. 2021Knowledge Graph-enhanced Sampling for Conversational Recommender Systemcited by 0
  32. 2024Perturbation-based Graph Active Learning for Weakly-Supervised Belief Representation Learningcited by 0
  33. 2025On The Expressive Power of GNN Derivativescited by 0
  34. 2026DREAM: Dual-Standard Semantic Homogeneity with Dynamic Optimization for Graph Learning with Label Noisecited by 0
  35. 2026An Approximation Algorithm for Graph Label Selectioncited by 0
  36. 2026Where LLM Annotators Fail: Label-Free Learning on Graphs with LLMscited by 0
  37. 2026ALINC: Active Learning for Inductive Node Classification via Graph Samplingcited by 0
  38. 2026GATTA: Graph Active Learning with Test-Time Augmentationcited by 0