Ranking Structured Objects with Graph Neural Networks

TL;DR

This paper introduces RankGNNs, a novel method combining graph neural networks with learning-to-rank techniques, demonstrating improved performance in ranking structured data like molecules for drug screening.

Contribution

The paper proposes RankGNNs, a new GNN-based ranking framework trained on pairwise preferences, advancing the application of GNNs in ranking tasks.

Findings

RankGNNs outperform naive GNN regression baselines.

RankGNNs match or exceed existing ranking methods in experiments.

Effective for drug candidate prioritization.

Abstract

Graph neural networks (GNNs) have been successfully applied in many structured data domains, with applications ranging from molecular property prediction to the analysis of social networks. Motivated by the broad applicability of GNNs, we propose the family of so-called RankGNNs, a combination of neural Learning to Rank (LtR) methods and GNNs. RankGNNs are trained with a set of pair-wise preferences between graphs, suggesting that one of them is preferred over the other. One practical application of this problem is drug screening, where an expert wants to find the most promising molecules in a large collection of drug candidates. We empirically demonstrate that our proposed pair-wise RankGNN approach either significantly outperforms or at least matches the ranking performance of the naive point-wise baseline approach, in which the LtR problem is solved via GNN-based graph regression.