arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.01358cs.LG
收藏

含时谐波延拓的学习标号法

Learning Label Initialization for Time-Dependent Harmonic Extension

University of Caen Normandy(卡昂诺曼底大学)

Amitoz Azad

摘要:

图上的节点分类可以用图上的Dirichlet问题来表示,其中信号在标记的节点处给出,而调和扩展在未标记的节点上完成。本文考虑了图上Dirichlet问题的一个时间依赖版本,并展示了如何通过学习未标记节点上的适当初始化向量来改进其解。此外,我们表明,改进的解决方案是在与国家的最先进的方法用于节点分类。最后,我们通过讨论参数t的重要性,优点和未来的发展方向来总结本文。

英文摘要:

Node classification on graphs can be formulated as the Dirichlet problem on graphs where the signal is given at the labeled nodes, and the harmonic extension is done on the unlabeled nodes. This paper considers a time-dependent version of the Dirichlet problem on graphs and shows how to improve its solution by learning the proper initialization vector on the unlabeled nodes. Further, we show that the improved solution is at par with state-of-the-art methods used for node classification. Finally, we conclude this paper by discussing the importance of parameter t, pros, and future directions.

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。

↑