# Graph Policy Network for Transferable Active Learning on Graphs

arXiv: https://arxiv.org/abs/2006.13463 · HTML: https://mlsanity.com/paper/2006.13463/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jun 2020.

## Built on by (most cited first, 30 of 50)

- [Handling Distribution Shifts on Graphs: An Invariance Perspective](https://mlsanity.com/paper/2202.02466/) (2022)
- [Label-free Node Classification on Graphs with Large Language Models (LLMS)](https://mlsanity.com/paper/2310.04668/) (2023)
- [A Survey on Deep Active Learning: Recent Advances and New Frontiers](https://mlsanity.com/paper/2405.00334/) (2024)
- [Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networks](https://mlsanity.com/paper/2108.01176/) (2021)
- [On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs](https://mlsanity.com/paper/2107.01495/) (2021)
- [RIM: Reliable Influence-based Active Learning on Graphs](https://mlsanity.com/paper/2110.14854/) (2021)
- [Uncertainty in Graph Neural Networks: A Survey](https://mlsanity.com/paper/2403.07185/) (2024)
- [Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities](https://mlsanity.com/paper/2506.18019/) (2025)
- [Data-centric Graph Learning: A Survey](https://mlsanity.com/paper/2310.04987/) (2023)
- [Reinforcement learning on graphs: A survey](https://mlsanity.com/paper/2204.06127/) (2022)
- [MentorGNN: Deriving Curriculum for Pre-Training GNNs](https://mlsanity.com/paper/2208.09905/) (2022)
- [Efficient Subgraph GNNs by Learning Effective Selection Policies](https://mlsanity.com/paper/2310.20082/) (2023)
- [Graph Neural Networks: Methods, Applications, and Opportunities](https://mlsanity.com/paper/2108.10733/) (2021)
- [Information Gain Propagation: a new way to Graph Active Learning with Soft Labels](https://mlsanity.com/paper/2203.01093/) (2022)
- [JuryGCN: Quantifying Jackknife Uncertainty on Graph Convolutional Networks](https://mlsanity.com/paper/2210.05959/) (2022)
- [Towards Data-centric Graph Machine Learning: Review and Outlook](https://mlsanity.com/paper/2309.10979/) (2023)
- [Partition-Based Active Learning for Graph Neural Networks](https://mlsanity.com/paper/2201.09391/) (2022)
- [Uncertainty for Active Learning on Graphs](https://mlsanity.com/paper/2405.01462/) (2024)
- [MAG-GNN: Reinforcement Learning Boosted Graph Neural Network](https://mlsanity.com/paper/2310.19142/) (2023)
- [LEGO-Learn: Label-Efficient Graph Open-Set Learning](https://mlsanity.com/paper/2410.16386/) (2024)
- [RELIEF: Reinforcement Learning Empowered Graph Feature Prompt Tuning](https://mlsanity.com/paper/2408.03195/) (2024)
- [EvoluNet: Advancing Dynamic Non-IID Transfer Learning on Graphs](https://mlsanity.com/paper/2305.00664/) (2023)
- [Reinforcement Learning Based Query Vertex Ordering Model for Subgraph Matching](https://mlsanity.com/paper/2201.11251/) (2022)
- [Poisson Reweighted Laplacian Uncertainty Sampling for Graph-based Active Learning](https://mlsanity.com/paper/2210.15786/) (2022)
- [Graph-Skeleton: ~1% Nodes are Sufficient to Represent Billion-Scale Graph](https://mlsanity.com/paper/2402.09565/) (2024)
- [Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality](https://mlsanity.com/paper/2501.03113/) (2025)
- [StriderNET: A Graph Reinforcement Learning Approach to Optimize Atomic Structures on Rough Energy Landscapes](https://mlsanity.com/paper/2301.12477/) (2023)
- [A Unified Active Learning Framework for Annotating Graph Data with Application to Software Source Code Performance Prediction](https://mlsanity.com/paper/2304.13032/) (2023)
- [SMARTQUERY: An Active Learning Framework for Graph Neural Networks through Hybrid Uncertainty Reduction](https://mlsanity.com/paper/2212.01440/) (2022)
- [Dissimilar Nodes Improve Graph Active Learning](https://mlsanity.com/paper/2212.01968/) (2022)

## 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.