Logo Logo
Switch Language to German
Damke, Clemens ORCID: 0000-0002-0455-0048; Hüllermeier, Eyke ORCID: 0000-0002-9944-4108 (11. October 2021): Ranking Structured Objects with Graph Neural Networks. 24th International Conference on Discovery Science (DS 2021), October 11–13, 2021, Halifax, NS, Canada, Virtual.
Full text not available from 'Open Access LMU'.


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 naïve point-wise baseline approach, in which the LtR problem is solved via GNN-based graph regression.