arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.08869cs.LG
收藏

基于图神经网络的结构化对象排序

Ranking Structured Objects with Graph Neural Networks

Heinz Nixdorf Institute(海因茨·尼克斯多夫研究所);Paderborn University(帕德博恩大学);Institute of Informatics(信息学研究所);University of Munich(慕尼黑大学)

Clemens Damke, Eyke Hüllermeier

摘要:

图神经网络(GNN)已成功应用于许多结构化数据领域,其应用范围从分子性质预测到社交网络分析。受GNNs广泛适用性的启发,我们提出了所谓的RankGNNs家族,这是神经学习排序(LtR)方法和GNNs的组合。RankGNN是用一组图之间的成对偏好来训练的,这表明其中一个比另一个更受欢迎。这个问题的一个实际应用是药物筛选,专家希望在大量候选药物中找到最有希望的分子。我们根据经验证明,我们提出的成对RankGNN方法显著优于或至少匹配朴素逐点基线方法的排名性能,其中LtR问题通过基于GNN的图回归来解决。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑