Metraipolis › archive › dc_663a97998f57
GATTA: Graph Active Learning with Test-Time Augmentation — arXiv:2608.15084
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.15084
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T17:57:46.899Z
- SHA-256 of the archived text
00515a7fec5e10cb6479b33328c92fda86ebe14f0754845549c44252f0a6ebc6- Stable URL of this page
https://metraipolis.com/documento/dc_663a97998f57
How to cite
GATTA: Graph Active Learning with Test-Time Augmentation — arXiv:2608.15084 — arXiv (en), https://arxiv.org/abs/2608.15084 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_663a97998f57 (Metraipolis archive dc_663a97998f57, sha256 00515a7fec5e10cb6479b33328c92fda86ebe14f0754845549c44252f0a6ebc6)
BibTeX
@misc{dc663a97998f57,
title = {GATTA: Graph Active Learning with Test-Time Augmentation — arXiv:2608.15084},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.15084},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_663a97998f57; sha256 00515a7fec5e10cb6479b33328c92fda86ebe14f0754845549c44252f0a6ebc6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15084. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.15084 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T16:29:13.982Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).