Conformal Prediction: A Theoretical Note and Benchmarking Transductive Node Classification in Graphs

TL;DR

This paper reviews conformal prediction in graph models, analyzes existing methods, and proposes scalable techniques for large graphs, providing theoretical and empirical insights for future research.

Contribution

It offers a comprehensive analysis of design choices in graph conformal prediction and introduces scalable methods validated through theoretical and empirical results.

Findings

Analysis of existing conformal graph prediction methods

Scalable techniques for large-scale graph datasets

Guidelines for future research in graph conformal prediction

Abstract

Conformal prediction has become increasingly popular for quantifying the uncertainty associated with machine learning models. Recent work in graph uncertainty quantification has built upon this approach for conformal graph prediction. The nascent nature of these explorations has led to conflicting choices for implementations, baselines, and method evaluation. In this work, we analyze the design choices made in the literature and discuss the tradeoffs associated with existing methods. Building on the existing implementations, we introduce techniques to scale existing methods to large-scale graph datasets without sacrificing performance. Our theoretical and empirical results justify our recommendations for future scholarship in graph conformal prediction.