Predict Confidently, Predict Right: Abstention in Dynamic Graph Learning

2025-01-14

AI Summary

In high-stakes decision-making scenarios on dynamic graphs—characterized by extreme class imbalance, low prediction confidence, and prohibitively high misclassification costs—this work introduces, for the first time, a rejection mechanism into continuous-time temporal graph neural networks (CT-TGNNs). We propose a coverage-driven adaptive rejection framework that jointly optimizes confidence estimation and coverage constraints, enabling robust training under class imbalance via uncertainty modeling and a reweighted loss function. Evaluated on four dynamic link prediction and two dynamic node classification benchmarks, our method achieves significant improvements in AUC and AP while maintaining high precision and controllable coverage. This enhances both model reliability and decision safety in critical applications.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Many real-world systems can be modeled as dynamic graphs, where nodes and edges evolve over time, requiring specialized models to capture their evolving dynamics in risk-sensitive applications effectively. Temporal graph neural networks (GNNs) are one such category of specialized models. For the first time, our approach integrates a reject option strategy within the framework of GNNs for continuous-time dynamic graphs. This allows the model to strategically abstain from making predictions when the uncertainty is high and confidence is low, thus minimizing the risk of critical misclassification and enhancing the results and reliability. We propose a coverage-based abstention prediction model to implement the reject option that maximizes prediction within a specified coverage. It improves the prediction score for link prediction and node classification tasks. Temporal GNNs deal with extremely skewed datasets for the next state prediction or node classification task. In the case of class imbalance, our method can be further tuned to provide a higher weightage to the minority class. Exhaustive experiments are presented on four datasets for dynamic link prediction and two datasets for dynamic node classification tasks. This demonstrates 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. The results highlight our model's ability to efficiently handle the trade-offs between prediction confidence and coverage, making it a dependable solution for applications requiring high precision in dynamic and uncertain environments.

Problem

• Time-Varying Graphs
• Imbalanced Data
• Prediction Accuracy

Innovation

• Rejection Prediction
• Temporal Graph Neural Networks
• Imbalanced Datasets