Predict Confidently, Predict Right: Abstention in Dynamic Graph Learning

TL;DR

This paper introduces a novel abstention strategy for temporal graph neural networks that improves prediction reliability in dynamic, uncertain environments by strategically abstaining when confidence is low.

Contribution

It is the first to integrate a reject option into GNNs for dynamic graphs, enhancing prediction accuracy and reliability with a coverage-based abstention model.

Findings

Improves link prediction and node classification scores.

Effectively handles class imbalance in dynamic graph tasks.

Demonstrates robustness across multiple datasets.

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.