arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1811.06237cs.SIcs.AIcs.LG
收藏

SGR:自监督谱图表示学习

SGR: Self-Supervised Spectral Graph Representation Learning

Hasso Plattner Institute(哈索·普拉特纳研究所);Aarhus University(奥胡斯大学);Technion(以色列理工学院)

Anton Tsitsulin, Davide Mottin, Panagiotis Karras, Alex Bronstein, Emmanuel Müller

摘要:

将图表示为向量是一项具有挑战性的任务;理想情况下,表示应该易于计算,并有助于图之间的有效比较,适合手头的特定数据和分析任务。不幸的是,一个“一刀切”的解决方案是无法实现的,因为不同的分析任务可能需要不同的关注全局或局部图的功能。我们开发的SGR,第一,据我们所知,方法学习图形表示在一个自我监督的方式。基于频谱图分析,SGR无缝地结合了所有上述理想的属性。在广泛的实验中,我们展示了我们的方法如何在大型图形集合上工作,促进跨各种应用领域的自我监督表示学习,并在无需重新训练的情况下与最先进的方法竞争。

英文摘要:

Representing a graph as a vector is a challenging task; ideally, the representation should be easily computable and conducive to efficient comparisons among graphs, tailored to the particular data and analytical task at hand. Unfortunately, a "one-size-fits-all" solution is unattainable, as different analytical tasks may require different attention to global or local graph features. We develop SGR, the first, to our knowledge, method for learning graph representations in a self-supervised manner. Grounded on spectral graph analysis, SGR seamlessly combines all aforementioned desirable properties. In extensive experiments, we show how our approach works on large graph collections, facilitates self-supervised representation learning across a variety of application domains, and performs competitively to state-of-the-art methods without re-training.

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。

↑