论文标题
图形上的通用函数近似
Universal Function Approximation on Graphs
论文作者
论文摘要
在这项工作中，我们生成了一个框架，用于在图同构类别上构建通用函数近似值。我们证明了该框架如何带有理论上可取的特性的集合并实现了新颖的分析。我们展示了这如何使我们能够在图形分类中的四个不同知名数据集和其他图形学习方法中的单独类别中实现最先进的性能。我们的方法灵感来自持续的同源性，NLP的依赖性解析以及多相关功能。基础算法的复杂性是O（#EDGES x #nodes），并且代码公开可用（https://github.com/bruel-gabrielsson/universal-function-function-approximation-ongraphs）。
In this work we produce a framework for constructing universal function approximators on graph isomorphism classes. We prove how this framework comes with a collection of theoretically desirable properties and enables novel analysis. We show how this allows us to achieve state-of-the-art performance on four different well-known datasets in graph classification and separate classes of graphs that other graph-learning methods cannot. Our approach is inspired by persistent homology, dependency parsing for NLP, and multivalued functions. The complexity of the underlying algorithm is O(#edges x #nodes) and code is publicly available (https://github.com/bruel-gabrielsson/universal-function-approximation-on-graphs).
