GETS: Ensemble Temperature Scaling for Calibration in Graph Neural Networks

TL;DR

This paper introduces GETS, a novel ensemble temperature scaling method for GNNs that improves calibration accuracy by leveraging input and model ensembles, outperforming existing techniques on multiple benchmarks.

Contribution

The paper presents Graph Ensemble Temperature Scaling (GETS), a new calibration framework that effectively combines input and model ensembles within a Graph Mixture of Experts architecture for GNNs.

Findings

Reduces expected calibration error by 25% across 10 datasets

Outperforms existing calibration methods in GNNs

Efficient and scalable implementation

Abstract

Graph Neural Networks deliver strong classification results but often suffer from poor calibration performance, leading to overconfidence or underconfidence. This is particularly problematic in high stakes applications where accurate uncertainty estimates are essential. Existing post hoc methods, such as temperature scaling, fail to effectively utilize graph structures, while current GNN calibration methods often overlook the potential of leveraging diverse input information and model ensembles jointly. In the paper, we propose Graph Ensemble Temperature Scaling, a novel calibration framework that combines input and model ensemble strategies within a Graph Mixture of Experts archi SOTA calibration techniques, reducing expected calibration error by 25 percent across 10 GNN benchmark datasets. Additionally, GETS is computationally efficient, scalable, and capable of selecting effective input combinations for improved calibration performance. The implementation is available via Github.