论文标题
通过广义读取功能改善图形属性预测
Improving Graph Property Prediction with Generalized Readout Functions
论文作者
论文摘要
由于图形是最通用的数据结构之一，因此近年来，Graph属性预测在近年来引起了人们的注意，因为它们可以包含任意数量的节点和它们之间的连接，并且它是许多不同任务（例如，网络，分子，知识库）等许多不同任务（例如分类和回归）的骨干。我们介绍了一个新颖的广义全球合并层，以减轻通常在读数阶段的信息丢失，这些信息损失在读取阶段。这个新颖的层是通过可以选择学习的两个值（$β$和$ p $）的参数，并且它执行的转换可以在某些设置下恢复到几个已经流行的读出函数（均值，最大和sum），可以指定。为了展示这种新颖技术的卓越表现力和性能，我们通过采用当前表现最佳的体系结构并将读出层作为倒入替换，我们在流行的图形属性预测任务中对其进行了测试，我们报告了最新的结果状态。可以在此处访问重现实验的代码：https：//github.com/ericalcaide/generalized-readout-phase-phase-phase
Graph property prediction is drawing increasing attention in the recent years due to the fact that graphs are one of the most general data structures since they can contain an arbitrary number of nodes and connections between them, and it is the backbone for many different tasks like classification and regression on such kind of data (networks, molecules, knowledge bases, ...). We introduce a novel generalized global pooling layer to mitigate the information loss that typically occurs at the Readout phase in Message-Passing Neural Networks. This novel layer is parametrized by two values ($β$ and $p$) which can optionally be learned, and the transformation it performs can revert to several already popular readout functions (mean, max and sum) under certain settings, which can be specified. To showcase the superior expressiveness and performance of this novel technique, we test it in a popular graph property prediction task by taking the current best-performing architecture and using our readout layer as a drop-in replacement and we report new state of the art results. The code to reproduce the experiments can be accessed here: https://github.com/EricAlcaide/generalized-readout-phase
