AbstainGNN: Teaching Graph Neural Networks to Abstain for Graph Classification

• URL: http://arxiv.org/abs/2605.30786v1
• Date: Fri, 29 May 2026 03:21:14 GMT
• Title: AbstainGNN: Teaching Graph Neural Networks to Abstain for Graph Classification
• Abstract summary: AbstainGNN is a novel and theory-driven framework for graph classification with abstention.<n>It explicitly models both the predictive function and the abstention function, allowing for effective utilization of graph structural information.<n>Experiments on five benchmark datasets show that AbstainGNN outperforms existing abstention methods.
• Score: 56.26852966986448
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph classification is a core task in graph data mining with widespread real-world applications. Recent advances in graph neural networks (GNNs) have led to substantial performance improvements for graph classification. However, existing GNNs are typically forced to make predictions even under high uncertainty or unknown conditions, resulting in unreliable decisions that can severely impact downstream tasks, particularly in safety-critical scenarios. To address this critical limitation, we propose AbstainGNN, a novel and theory-driven framework for graph classification with abstention, which enables GNNs to reject uncertain predictions instead of producing incorrect decisions. Specifically, AbstainGNN explicitly models both the predictive function and the abstention function, allowing for effective utilization of graph structural information. Moreover, unlike existing heuristic abstention methods, we theoretically characterize the trade-off between classification errors and rejection costs from a PAC-Bayesian generalization perspective, and derive a unified learning objective for model optimization. Guided by this theoretical insight, we further develop an efficient two-stage training strategy consisting of predictive function warm-start and abstention function calibration. Extensive experiments on five benchmark datasets show that AbstainGNN outperforms existing abstention methods, achieving superior classification performance under the same rejection rates.

Related papers

• Two Birds with One Stone: Enhancing Uncertainty Quantification and Interpretability with Graph Functional Neural Process [27.760002432327962]
  Graph neural networks (GNNs) are powerful tools on graph data.<n>However, their predictions are mis-calibrated and lack interpretability.<n>We propose a new uncertainty-aware and interpretable graph classification model.
  arXiv  Detail & Related papers  (2025-08-23T17:48:05Z)
• Predict Confidently, Predict Right: Abstention in Dynamic Graph Learning [6.0497759658090775]
  We propose a reject option strategy within the framework of temporal graph neural networks (GNNs) for continuous-time dynamic graphs.<n>This allows the model to strategically abstain from making predictions when the uncertainty is high and confidence is low.<n>We show the effectiveness of our approach in improving the reliability and area under the curve (AUC)/ average precision (AP) scores for predictions in dynamic graph scenarios.
  arXiv  Detail & Related papers  (2025-01-14T19:27:58Z)
• Revisiting Graph Neural Networks on Graph-level Tasks: Comprehensive Experiments, Analysis, and Improvements [54.006506479865344]
  We propose a unified evaluation framework for graph-level Graph Neural Networks (GNNs)<n>This framework provides a standardized setting to evaluate GNNs across diverse datasets.<n>We also propose a novel GNN model with enhanced expressivity and generalization capabilities.
  arXiv  Detail & Related papers  (2025-01-01T08:48:53Z)
• Kolmogorov-Arnold Graph Neural Networks [2.4005219869876453]
  Graph neural networks (GNNs) excel in learning from network-like data but often lack interpretability.<n>We propose the Graph Kolmogorov-Arnold Network (GKAN) to enhance both accuracy and interpretability.
  arXiv  Detail & Related papers  (2024-06-26T13:54:59Z)
• Online GNN Evaluation Under Test-time Graph Distribution Shifts [92.4376834462224]
  A new research problem, online GNN evaluation, aims to provide valuable insights into the well-trained GNNs's ability to generalize to real-world unlabeled graphs. We develop an effective learning behavior discrepancy score, dubbed LeBeD, to estimate the test-time generalization errors of well-trained GNN models.
  arXiv  Detail & Related papers  (2024-03-15T01:28:08Z)
• GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labels [81.93520935479984]
  We study a new problem, GNN model evaluation, that aims to assess the performance of a specific GNN model trained on labeled and observed graphs. We propose a two-stage GNN model evaluation framework, including (1) DiscGraph set construction and (2) GNNEvaluator training and inference. Under the effective training supervision from the DiscGraph set, GNNEvaluator learns to precisely estimate node classification accuracy of the to-be-evaluated GNN model.
  arXiv  Detail & Related papers  (2023-10-23T05:51:59Z)
• MentorGNN: Deriving Curriculum for Pre-Training GNNs [61.97574489259085]
  We propose an end-to-end model named MentorGNN that aims to supervise the pre-training process of GNNs across graphs. We shed new light on the problem of domain adaption on relational data (i.e., graphs) by deriving a natural and interpretable upper bound on the generalization error of the pre-trained GNNs.
  arXiv  Detail & Related papers  (2022-08-21T15:12:08Z)
• Optimal Propagation for Graph Neural Networks [51.08426265813481]
  We propose a bi-level optimization approach for learning the optimal graph structure. We also explore a low-rank approximation model for further reducing the time complexity.
  arXiv  Detail & Related papers  (2022-05-06T03:37:00Z)
• A Graph Data Augmentation Strategy with Entropy Preserving [11.886325179121226]
  We introduce a novel graph entropy definition as a quantitative index to evaluate feature information among a graph. Under considerations of preserving graph entropy, we propose an effective strategy to generate training data using a perturbed mechanism. Our proposed approach significantly enhances the robustness and generalization ability of GCNs during the training process.
  arXiv  Detail & Related papers  (2021-07-13T12:58:32Z)

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.