Enhancing Trustworthiness of Graph Neural Networks with Rank-Based Conformal Training

TL;DR

This paper introduces RCP-GNN, a novel training framework for Graph Neural Networks that uses rank-based conformal prediction to produce reliable, statistically guaranteed uncertainty estimates, improving trustworthiness in node classification tasks.

Contribution

The paper proposes a rank-based conformal prediction method integrated into GNN training, enabling adaptive, reliable uncertainty estimation with theoretical coverage guarantees.

Findings

Achieves desired coverage with reduced inefficiency.

Outperforms state-of-the-art methods in real-world datasets.

Provides statistically guaranteed uncertainty estimates.

Abstract

Graph Neural Networks (GNNs) has been widely used in a variety of fields because of their great potential in representing graph-structured data. However, lacking of rigorous uncertainty estimations limits their application in high-stakes. Conformal Prediction (CP) can produce statistically guaranteed uncertainty estimates by using the classifier's probability estimates to obtain prediction sets, which contains the true class with a user-specified probability. In this paper, we propose a Rank-based CP during training framework to GNNs (RCP-GNN) for reliable uncertainty estimates to enhance the trustworthiness of GNNs in the node classification scenario. By exploiting rank information of the classifier's outcome, prediction sets with desired coverage rate can be efficiently constructed. The strategy of CP during training with differentiable rank-based conformity loss function is further explored to adapt prediction sets according to network topology information. In this way, the composition of prediction sets can be guided by the goal of jointly reducing inefficiency and probability estimation errors. Extensive experiments on several real-world datasets show that our model achieves any pre-defined target marginal coverage while significantly reducing the inefficiency compared with state-of-the-art methods.