GATTA: Graph Active Learning with Test-Time Augmentation

• URL: http://arxiv.org/abs/2608.15084v1
• Date: Sat, 15 Aug 2026 07:01:59 GMT
• Title: GATTA: Graph Active Learning with Test-Time Augmentation
• Abstract summary: Test-time augmentation (TTA) has proven effective for improving model robustness and uncertainty estimation in computer vision.<n>We introduce GATTA (Graph Active Learning with Test-Time Augmentation), a framework for enhancing active learning by aggregating predictions across multiple augmented views.
• Score: 0.056179939237156
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Towards Improving Long-Tail Entity Predictions in Temporal Knowledge Graphs through Global Similarity and Weighted Sampling [53.11315884128402]
  Temporal Knowledge Graph (TKG) completion models traditionally assume access to the entire graph during training.<n>We present an incremental training framework specifically designed for TKGs, aiming to address entities that are either not observed during training or have sparse connections.<n>Our approach combines a model-agnostic enhancement layer with a weighted sampling strategy, that can be augmented to and improve any existing TKG completion method.
  arXiv  Detail & Related papers  (2025-07-25T06:02:48Z)
• Efficient Knowledge Tracing Leveraging Higher-Order Information in Integrated Graphs [2.4134741591214808]
  We introduce Dual Graph Attention-based Knowledge Tracing (DGAKT)<n>It is a graph neural network model designed to leverage high-order information from subgraphs representing student-exercise-KC relationships.<n>It significantly reduces memory and computational requirements compared to full global graph models.
  arXiv  Detail & Related papers  (2025-07-24T06:12:43Z)
• Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering [75.12322966980003]
  Large Language Models (LLMs) have shown strong inductive reasoning ability across various domains.<n>Most existing RAG pipelines rely on unstructured text, limiting interpretability and structured reasoning.<n>Recent studies have explored integrating knowledge graphs with LLMs for knowledge graph question answering.<n>We propose RAPL, a novel framework for efficient and effective graph retrieval in KGQA.
  arXiv  Detail & Related papers  (2025-06-11T12:03:52Z)
• Enhancing Training Data Attribution with Representational Optimization [57.61977909113113]
  Training data attribution methods aim to measure how training data impacts a model's predictions.<n>We propose AirRep, a representation-based approach that closes this gap by learning task-specific and model-aligned representations explicitly for TDA.<n>AirRep introduces two key innovations: a trainable encoder tuned for attribution quality, and an attention-based pooling mechanism that enables accurate estimation of group-wise influence.
  arXiv  Detail & Related papers  (2025-05-24T05:17:53Z)
• GAIS: A Novel Approach to Instance Selection with Graph Attention Networks [1.100197352932064]
  This paper introduces a novel method called Graph Attention-based Instance Selection (GAIS) to identify the most informative instances in a dataset.<n>Experiments on 13 diverse datasets demonstrate that GAIS consistently outperforms traditional IS methods in terms of effectiveness.<n>Although GAIS exhibits slightly higher computational costs, its superior performance in maintaining accuracy with significantly reduced training data makes it a promising approach for graph-based data selection.
  arXiv  Detail & Related papers  (2024-12-26T12:51:14Z)
• Enhancing Heterogeneous Knowledge Graph Completion with a Novel GAT-based Approach [3.8357926394952306]
  We propose a novel GAT-based knowledge graph completion method for Heterogeneous knowledge graphs. GATH incorporates two separate attention network modules that work synergistically to predict the missing entities. Our model improves performance by 5.2% and 5.2% on the FB15K-237 dataset and by 4.5% and 14.6% on the WN18RR dataset.
  arXiv  Detail & Related papers  (2024-08-05T13:28:51Z)
• Graph Transductive Defense: a Two-Stage Defense for Graph Membership Inference Attacks [50.19590901147213]
  Graph neural networks (GNNs) have become instrumental in diverse real-world applications, offering powerful graph learning capabilities. GNNs are vulnerable to adversarial attacks, including membership inference attacks (MIA) This paper proposes an effective two-stage defense, Graph Transductive Defense (GTD), tailored to graph transductive learning characteristics.
  arXiv  Detail & Related papers  (2024-06-12T06:36:37Z)
• GReAT: A Graph Regularized Adversarial Training Method [0.0]
  GReAT (Graph Regularized Adversarial Training) is a novel regularization method designed to enhance the robust classification performance of deep learning models. GReAT integrates graph based regularization into the adversarial training process, leveraging the data's inherent structure to enhance model robustness.
  arXiv  Detail & Related papers  (2023-10-09T01:44:06Z)
• LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation [9.181689366185038]
  Graph neural clustering network (GNN) is a powerful learning approach for graph-based recommender systems. In this paper, we propose a simple yet effective graph contrastive learning paradigm LightGCL.
  arXiv  Detail & Related papers  (2023-02-16T10:16:21Z)
• Adaptive Depth Graph Attention Networks [19.673509341792606]
  The graph attention networks (GAT) is considered the most advanced learning architecture for graph representation. We find that the main factor limiting the accuracy of the GAT model as the number of layers increases is the oversquashing phenomenon. We propose a GAT variant model-ADGAT that adaptively selects the number of layers based on the sparsity of the graph.
  arXiv  Detail & Related papers  (2023-01-16T05:22:29Z)
• Localized Contrastive Learning on Graphs [110.54606263711385]
  We introduce a simple yet effective contrastive model named Localized Graph Contrastive Learning (Local-GCL) In spite of its simplicity, Local-GCL achieves quite competitive performance in self-supervised node representation learning tasks on graphs with various scales and properties.
  arXiv  Detail & Related papers  (2022-12-08T23:36:00Z)
• Model-Agnostic Graph Regularization for Few-Shot Learning [60.64531995451357]
  We present a comprehensive study on graph embedded few-shot learning. We introduce a graph regularization approach that allows a deeper understanding of the impact of incorporating graph information between labels. Our approach improves the performance of strong base learners by up to 2% on Mini-ImageNet and 6.7% on ImageNet-FS.
  arXiv  Detail & Related papers  (2021-02-14T05:28:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.