mlsanityData to 7 Oct 2026

Partition-Based Active Learning for Graph Neural Networks

arXiv 2201.09391 ↗First posted 23 Jan 2022cs.LG cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

We study the problem of semi-supervised learning with Graph Neural Networks (GNNs) in an active learning setup. We propose GraphPart, a novel partition-based active learning approach for GNNs. GraphPart first splits the graph into disjoint partitions and then selects representative nodes within each partition to query. The proposed method is motivated by a novel analysis of the classification error under realistic smoothness assumptions over the graph and the node features. Extensive experiments on multiple benchmark datasets demonstrate that the proposed method outperforms existing active learning methods for GNNs under a wide range of annotation budget constraints. In addition, the proposed method does not introduce additional hyperparameters, which is crucial for model training, especially in the active learning setting where a labeled validation set may not be available.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 22 of its 54 references that are in the map. First posted on arXiv 23 Jan 2022.

Builds on

22 of 54 references.

References · 22

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  5. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  6. 2019Simplifying Graph Convolutional Networkscited by 1,470
  7. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  8. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  9. 2020A Survey of Deep Active Learningcited by 547
  10. 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 332
  11. 2017A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networkscited by 309
  12. 2018Contextual Stochastic Block Modelscited by 134
10 more
  1. 2021Subgroup Generalization and Fairness of Graph Neural Networkscited by 69
  2. 2017Active Learning for Graph Embeddingcited by 53
  3. 2020Graph Policy Network for Transferable Active Learning on Graphscited by 49
  4. 2019Active Learning for Graph Neural Networks via Node Feature Propagationcited by 37
  5. 2015S2: An Efficient Graph Based Active Learning Algorithm with Application to Nonparametric Classificationcited by 20
  6. 2017Near-Optimal Discrete Optimization for Experimental Design: A Regret Minimization Approachcited by 19
  7. 2019ActiveHNE: Active Heterogeneous Network Embeddingcited by 11
  8. 2019SEAL: Semi-supervised Adversarial Active Learning on Attributed Graphscited by 11
  9. 2017A Meta-Learning Approach to One-Step Active Learningcited by 9
  10. 2020Active Learning on Attributed Graphs via Graph Cognizant Logistic Regression and Preemptive Query Generationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 3; 2025: 3; 2026: 2.

12 papers.

  1. 2023Label-free Node Classification on Graphs with Large Language Models (LLMS)cited by 72
  2. 2025Model Generalization on Text Attribute Graphs: Principles with Large Language Modelscited by 8
  3. 2022Dissimilar Nodes Improve Graph Active Learningcited by 3
  4. 2023Towards Label Position Bias in Graph Neural Networkscited by 3
  5. 2024On the Topology Awareness and Generalization Performance of Graph Neural Networkscited by 3
  6. 2024Robust Offline Active Learning on Graphscited by 3
  7. 2024DELTA: Dual Consistency Delving with Topological Uncertainty for Active Graph Domain Adaptationcited by 2
  8. 2025Language Models as Messengers: Enhancing Message Passing in Heterophilic Graph Learningcited by 2
  9. 2023A Structural-Clustering Based Active Learning for Graph Neural Networkscited by 1
  10. 2025GRAIL: A Benchmark for GRaph ActIve Learning in Dynamic Sensing Environmentscited by 0
  11. 2026ALINC: Active Learning for Inductive Node Classification via Graph Samplingcited by 0
  12. 2026LoGIC: Budgeted Context Construction for Node-Level Graph In-Context Learning with Tabular Foundation Modelscited by 0