GNNRank: Learning Global Rankings from Pairwise Comparisons via Directed Graph Neural Networks

TL;DR

GNNRank introduces a neural network framework using directed graph neural networks to recover global rankings from pairwise comparison data, outperforming baselines and demonstrating transferability.

Contribution

It proposes a novel GNN-based approach with digraph embedding and new objectives for ranking recovery, incorporating an inductive bias through Fiedler vector unfolding.

Findings

Achieves competitive and superior performance on various datasets.

Demonstrates promising transfer learning capabilities.

Provides a new neural network framework for ranking from pairwise comparisons.

Abstract

Recovering global rankings from pairwise comparisons has wide applications from time synchronization to sports team ranking. Pairwise comparisons corresponding to matches in a competition can be construed as edges in a directed graph (digraph), whose nodes represent e.g. competitors with an unknown rank. In this paper, we introduce neural networks into the ranking recovery problem by proposing the so-called GNNRank, a trainable GNN-based framework with digraph embedding. Moreover, new objectives are devised to encode ranking upsets/violations. The framework involves a ranking score estimation approach, and adds an inductive bias by unfolding the Fiedler vector computation of the graph constructed from a learnable similarity matrix. Experimental results on extensive data sets show that our methods attain competitive and often superior performance against baselines, as well as showing promising transfer ability. Codes and preprocessed data are at: \url{https://github.com/SherylHYX/GNNRank}.