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 2009.09919cs.LGstat.ML
收藏

利用广义Readout函数改进图属性预测

Improving Graph Property Prediction with Generalized Readout Functions

Eric Alcaide

AI总结:

针对图属性预测中消息传递神经网络Readout阶段信息损失问题,提出由β和p参数化、可退化为常见readout函数的广义全局池化层,替换现有最优架构的对应层后取得新的SOTA结果。

摘要:

图属性预测近年来受到越来越多的关注,因为图是最通用的数据结构之一,可包含任意数量的节点及节点间连接,也是网络、分子、知识库等这类数据上分类、回归等诸多不同任务的基础。我们提出了一种新型广义全局池化层,以缓解消息传递神经网络(Message-Passing Neural Networks)在Readout阶段通常出现的信息损失问题。该新型层由两个可选择学习的参数($β$和$p$)参数化,其执行的变换在特定设置下可退化为几种已流行的readout函数(均值、最大值、求和),这些设置可预先指定。为展示该新技术更优的表达能力和性能,我们在一项主流图属性预测任务中对其进行测试,采用当前性能最优的架构,将我们的readout层作为即插即用替换组件,并取得了新的 state of the art 结果。复现实验的代码可通过以下链接获取:https://github.com/EricAlcaide/generalized-readout-phase

英文摘要:

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

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。

↑