mlsanityData to 7 Oct 2026

Uncertainty for Active Learning on Graphs

arXiv 2405.01462 ↗First posted 2 May 2024cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

Uncertainty Sampling is an Active Learning strategy that aims to improve the data efficiency of machine learning models by iteratively acquiring labels of data points with the highest uncertainty. While it has proven effective for independent data its applicability to graphs remains under-explored. We propose the first extensive study of Uncertainty Sampling for node classification: (1) We benchmark Uncertainty Sampling beyond predictive uncertainty and highlight a significant performance gap to other Active Learning strategies. (2) We develop ground-truth Bayesian uncertainty estimates in terms of the data generating process and prove their effectiveness in guiding Uncertainty Sampling toward optimal queries. We confirm our results on synthetic data and design an approximate approach that consistently outperforms other uncertainty estimators on real datasets. (3) Based on this analysis, we relate pitfalls in modeling uncertainty to existing methods. Our analysis enables and informs the development of principled uncertainty estimation on graphs.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 35 of its 66 references that are in the map. First posted on arXiv 2 May 2024.

Builds on

35 of 66 references.

References · 35

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  3. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  4. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  5. 2019Simplifying Graph Convolutional Networkscited by 1,470
  6. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  7. 2017Deep Bayesian Active Learning with Image Datacited by 812
  8. 2015Image-based Recommendations on Styles and Substitutescited by 702
  9. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  10. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  11. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  12. 2015Weight Uncertainty in Neural Networkscited by 554
23 more
  1. 2020A Survey of Deep Active Learningcited by 547
  2. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  3. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 402
  4. 2019Learning Loss for Active Learningcited by 335
  5. 2019Variational Adversarial Active Learningcited by 284
  6. 2018Contextual Stochastic Block Modelscited by 134
  7. 2019Deep Active Learning: Unified and Principled Method for Query and Trainingcited by 92
  8. 2021Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classificationcited by 79
  9. 2023Energy-based Out-of-Distribution Detection for Graph Neural Networkscited by 67
  10. 2020Mat'ern Gaussian Processes on Graphscited by 65
  11. 2017Active Learning for Graph Embeddingcited by 53
  12. 2020Graph Policy Network for Transferable Active Learning on Graphscited by 49
  13. 2022What Makes Graph Neural Networks Miscalibrated?cited by 39
  14. 2019Active Learning for Graph Neural Networks via Node Feature Propagationcited by 37
  15. 2022GALAXY: Graph-based Active Learning at the Extremecited by 29
  16. 2015S2: An Efficient Graph Based Active Learning Algorithm with Application to Nonparametric Classificationcited by 20
  17. 2022Information Gain Propagation: a new way to Graph Active Learning with Soft Labelscited by 16
  18. 2019SEAL: Semi-supervised Adversarial Active Learning on Attributed Graphscited by 11
  19. 2023Stream-based Active Learning by Exploiting Temporal Properties in Perception with Temporal Predicted Losscited by 6
  20. 2016Graph-Based Active Learning: A New Look at Expected Error Minimizationcited by 4
  21. 2020Active Learning on Attributed Graphs via Graph Cognizant Logistic Regression and Preemptive Query Generationcited by 4
  22. 2022SMARTQUERY: An Active Learning Framework for Graph Neural Networks through Hybrid Uncertainty Reductioncited by 3
  23. 2017Data-adaptive Active Sampling for Efficient Graph-Cognizant Classificationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 7; 2026: 2.

11 papers.

  1. 2025Federated Learning with Sample-level Client Drift Mitigationcited by 6
  2. 2025Joint Out-of-Distribution Filtering and Data Discovery Active Learningcited by 6
  3. 2025Enhancing Cost Efficiency in Active Learning with Candidate Set Querycited by 3
  4. 2024DELTA: Dual Consistency Delving with Topological Uncertainty for Active Graph Domain Adaptationcited by 2
  5. 2024Active Prompt Learning with Vision-Language Model Priorscited by 2
  6. 2025Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theorycited by 2
  7. 2025Shapley-Guided Utility Learning for Effective Graph Inference Data Valuationcited by 1
  8. 2025Efficient Data Selection for Training Genomic Perturbation Modelscited by 0
  9. 2025RANA: Robust Active Learning for Noisy Network Alignmentcited by 0
  10. 2026ALINC: Active Learning for Inductive Node Classification via Graph Samplingcited by 0
  11. 2026SUGFW+: An Uncertainty-guided Feature Weighting Framework for Cold Start Active Adaptation of SAM in Medical Image Segmentationcited by 0