# GATTA: Graph Active Learning with Test-Time Augmentation

arXiv: https://arxiv.org/abs/2608.15084 · HTML: https://mlsanity.com/paper/2608.15084/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 46 references that are in the map.
- First posted on arXiv 15 Aug 2026.

## Builds on (most cited first, 30 of 32)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [DropEdge: Towards Deep Graph Convolutional Networks on Node Classification](https://mlsanity.com/paper/1907.10903/) (2019)
- [GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training](https://mlsanity.com/paper/2006.09963/) (2020)
- [Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks](https://mlsanity.com/paper/1807.07356/) (2018)
- [Data Augmentation for Graph Neural Networks](https://mlsanity.com/paper/2006.06830/) (2020)
- [Data Augmentation for Deep Graph Learning: A Survey](https://mlsanity.com/paper/2202.08235/) (2022)
- [Bayesian graph convolutional neural networks for semi-supervised classification](https://mlsanity.com/paper/1811.11103/) (2018)
- [Active Learning for Graph Embedding](https://mlsanity.com/paper/1705.05085/) (2017)
- [Local Augmentation for Graph Neural Networks](https://mlsanity.com/paper/2109.03856/) (2021)
- [Graph Policy Network for Transferable Active Learning on Graphs](https://mlsanity.com/paper/2006.13463/) (2020)
- [COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning](https://mlsanity.com/paper/2206.04726/) (2022)
- [GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation](https://mlsanity.com/paper/2310.00800/) (2023)
- [Uncertainty in Graph Neural Networks: A Survey](https://mlsanity.com/paper/2403.07185/) (2024)
- [Automated Data Augmentations for Graph Classification](https://mlsanity.com/paper/2202.13248/) (2022)
- [Label-invariant Augmentation for Semi-Supervised Graph Classification](https://mlsanity.com/paper/2205.09802/) (2022)
- [JuryGCN: Quantifying Jackknife Uncertainty on Graph Convolutional Networks](https://mlsanity.com/paper/2210.05959/) (2022)
- [Uncertainty for Active Learning on Graphs](https://mlsanity.com/paper/2405.01462/) (2024)
- [Improved Text Classification via Test-Time Augmentation](https://mlsanity.com/paper/2206.13607/) (2022)
- [Approaching Test Time Augmentation in the Context of Uncertainty Calibration for Deep Neural Networks](https://mlsanity.com/paper/2304.05104/) (2023)

## Abstract (arXiv)

Test-time augmentation (TTA) has proven effective for improving model robustness and uncertainty estimation in computer vision, yet its application to graph-structured data remains largely unexplored. We introduce GATTA (Graph Active Learning with Test-Time Augmentation), a framework for enhancing active learning by aggregating predictions across multiple augmented views to produce more reliable uncertainty estimates. To address the challenge of label-preserving graph augmentations, GATTA incorporates a consistency-based filtering mechanism that discards augmented views yielding unreliable predictions. We systematically evaluate GATTA across multiple graph datasets, GNN architectures, and acquisition strategies. Our results show that simple uncertainty-based methods, such as Entropy and Least Confidence, benefit most from TTA, achieving performance competitive with more sophisticated and computationally expensive approaches. GATTA generalizes across architectures, outperforms model-side ensemble methods such as MC Dropout. We further show that GATTA scales efficiently with both ensemble size and graph size. Extensive analysis of augmentation types, strengths, and filtering strategies provides practical guidelines for effective deployment. Our findings demonstrate that augmenting simple methods with TTA offers a more efficient path to strong active learning performance than engineering complex acquisition functions, enabling practitioners to achieve competitive results with lower computational overhead and reduced implementation complexity.