Timezone: »

GNNRank: Learning Global Rankings from Pairwise Comparisons via Directed Graph Neural Networks
Yixuan He · Quan Gan · David Wipf · Gesine Reinert · Junchi Yan · Mihai Cucuringu

Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ #422

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}.

Author Information

Yixuan He (University of Oxford)
Quan Gan (Amazon)
David Wipf (Microsoft Research)
Gesine Reinert (University of Oxford)
Gesine Reinert

Gesine Reinert is a University Professor in Statistics at the University of Oxford. She is a Fellow of Keble College, Oxford, a Fellow of the Alan Turing Institute, and a Fellow of the Institute of Mathematical Statistics.Her research interests include network analysis, models for biological data, and applied probability.

Junchi Yan (Shanghai Jiao Tong University)
Mihai Cucuringu (University of Oxford and The Alan Turing Institute)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors