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 1811.06930cs.LGstat.ML
收藏

带核的预训练图神经网络

Pre-training Graph Neural Networks with Kernels

University of Padova(帕多瓦大学);University of Freiburg(弗莱堡大学)

Nicolò Navarin, Dinh V. Tran, Alessandro Sperduti

摘要:

在过去的几年中,已经提出了许多机器学习技术来处理以图形结构形式表示的数据。图形可用于模拟多种场景,从分子和材料到RNA二级结构。在图上定义了几种核函数,再加上核化的学习算法,在许多任务上都表现出了最先进的性能。近年来,人们提出了几种图的神经网络(GNNs)的定义,但其准确性还不令人满意。在本文中,我们提出了一种与任务无关的预训练方法,该方法允许GNN学习由最先进的图内核诱导的表示。然后,监督学习阶段将为手头的任务微调这种表示。所提出的技术对所采用的GNN架构和核函数是不可知的,并且在我们的初步实验结果中显示了GNN预测性能的一致改进。

英文摘要:

Many machine learning techniques have been proposed in the last few years to process data represented in graph-structured form. Graphs can be used to model several scenarios, from molecules and materials to RNA secondary structures. Several kernel functions have been defined on graphs that coupled with kernelized learning algorithms, have shown state-of-the-art performances on many tasks. Recently, several definitions of Neural Networks for Graph (GNNs) have been proposed, but their accuracy is not yet satisfying. In this paper, we propose a task-independent pre-training methodology that allows a GNN to learn the representation induced by state-of-the-art graph kernels. Then, the supervised learning phase will fine-tune this representation for the task at hand. The proposed technique is agnostic on the adopted GNN architecture and kernel function, and shows consistent improvements in the predictive performance of GNNs in our preliminary experimental results.

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。

↑