Graph Sparsification for Enhanced Conformal Prediction in Graph Neural Networks

TL;DR

This paper introduces SparGCP, a novel graph sparsification method integrated into GNN training to improve conformal prediction efficiency and accuracy, reducing prediction set sizes and enhancing scalability.

Contribution

It presents a new training approach that incorporates graph sparsification and conformal prediction objectives, addressing the gap in training-stage improvements for GNN-based conformal prediction.

Findings

Reduces prediction set sizes by an average of 32%.

Outperforms existing methods on real-world datasets.

Scales effectively to large networks on commodity GPUs.

Abstract

Conformal Prediction is a robust framework that ensures reliable coverage across machine learning tasks. Although recent studies have applied conformal prediction to graph neural networks, they have largely emphasized post-hoc prediction set generation. Improving conformal prediction during the training stage remains unaddressed. In this work, we tackle this challenge from a denoising perspective by introducing SparGCP, which incorporates graph sparsification and a conformal prediction-specific objective into GNN training. SparGCP employs a parameterized graph sparsification module to filter out task-irrelevant edges, thereby improving conformal prediction efficiency. Extensive experiments on real-world graph datasets demonstrate that SparGCP outperforms existing methods, reducing prediction set sizes by an average of 32\% and scaling seamlessly to large networks on commodity GPUs.