Conformal Prediction for Federated Graph Neural Networks with Missing Neighbor Information

TL;DR

This paper extends conformal prediction to federated graph neural networks, addressing missing neighbor data with a VAE-based reconstruction method to improve uncertainty quantification and prediction reliability.

Contribution

It introduces a novel approach combining conformal prediction with VAE-based neighbor reconstruction for federated GNNs with missing data.

Findings

Smaller prediction sets with maintained coverage guarantees.

Effective reconstruction of missing neighbors improves model reliability.

Empirical results on real datasets validate the approach.

Abstract

Graphs play a crucial role in data mining and machine learning, representing real-world objects and interactions. As graph datasets grow, managing large, decentralized subgraphs becomes essential, particularly within federated learning frameworks. These frameworks face significant challenges, including missing neighbor information, which can compromise model reliability in safety-critical settings. Deployment of federated learning models trained in such settings necessitates quantifying the uncertainty of the models. This study extends the applicability of Conformal Prediction (CP), a well-established method for uncertainty quantification, to federated graph learning. We specifically tackle the missing links issue in distributed subgraphs to minimize its adverse effects on CP set sizes. We discuss data dependencies across the distributed subgraphs and establish conditions for CP validity and precise test-time coverage. We introduce a Variational Autoencoder-based approach for reconstructing missing neighbors to mitigate the negative impact of missing data. Empirical evaluations on real-world datasets demonstrate the efficacy of our approach, yielding smaller prediction sets while ensuring coverage guarantees.