面向 GNN 的通勤时间优化图
Commute-Time-Optimised Graphs for GNNs
AI总结:
针对带专家先验的图重连问题,本文提出两种纳入节点对交互先验、优化特权节点对通勤时间的定制方法,并在合成数据集和真实引文图上验证其效果。
摘要:
我们探索了优化通勤时间的图重连方法。近期的图重连方法促进了稀疏图中的长程交互,使此类重连在平均意义上达到通勤时间最优。然而,当存在关于哪些节点对应当或不应当交互的专家先验时,更优的重连会偏向于让这些特权节点对之间具有较短的通勤时间。我们构建了两个具有已知先验、反映现实设置的合成数据集,并以此为动机提出两种纳入该已知先验的定制重连方法。我们研究了我们的重连在合成数据集上提升测试性能的参数区间。最后,我们在真实引文图上进行案例研究,以考察本工作的实际意义。
英文摘要:
We explore graph rewiring methods that optimise commute time. Recent graph rewiring approaches facilitate long-range interactions in sparse graphs, making such rewirings commute-time-optimal on average. However, when an expert prior exists on which node pairs should or should not interact, a superior rewiring would favour short commute times between these privileged node pairs. We construct two synthetic datasets with known priors reflecting realistic settings, and use these to motivate two bespoke rewiring methods that incorporate the known prior. We investigate the regimes where our rewiring improves test performance on the synthetic datasets. Finally, we perform a case study on a real-world citation graph to investigate the practical implications of our work.
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。