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 2006.10252cs.LGstat.ML
收藏

图表示学习应用中的量化挑战

Quantifying Challenges in the Application of Graph Representation Learning

Capital One(第一资本)

Antonia Gogoglou, C. Bayan Bruss, Brian Nguyen, Reza Sarshogh, Keegan E. Hines

摘要:

图表示学习(GRL)作为一种以有意义的方式为后续学习任务提取结构信息的手段,已经经历了重大的进展。目前的方法,包括浅嵌入和图神经网络大多已测试与节点分类和链接预测任务。在这项工作中,我们提供了一个面向应用程序的角度来看,一组流行的嵌入方法,并评估其代表性的权力与现实世界的图形属性。我们实施了一个广泛的经验数据驱动的框架,以挑战现有的规范,在不同模式的图形中嵌入方法的表达能力,以及我们在这个过程中发现的局限性的理论分析。我们的研究结果表明,“一对一”的GRL方法是很难定义在现实世界中的情况下,随着新的方法被引入,他们应该明确他们的能力,捕捉图形属性和他们的适用性在数据集与非平凡的结构差异。

英文摘要:

Graph Representation Learning (GRL) has experienced significant progress as a means to extract structural information in a meaningful way for subsequent learning tasks. Current approaches including shallow embeddings and Graph Neural Networks have mostly been tested with node classification and link prediction tasks. In this work, we provide an application oriented perspective to a set of popular embedding approaches and evaluate their representational power with respect to real-world graph properties. We implement an extensive empirical data-driven framework to challenge existing norms regarding the expressive power of embedding approaches in graphs with varying patterns along with a theoretical analysis of the limitations we discovered in this process. Our results suggest that "one-to-fit-all" GRL approaches are hard to define in real-world scenarios and as new methods are being introduced they should be explicit about their ability to capture graph properties and their applicability in datasets with non-trivial structural differences.

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。

↑