arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.09300cs.LGcs.CV
收藏

特征相关聚合:通往更好的图神经网络的道路

Feature Correlation Aggregation: on the Path to Better Graph Neural Networks

Australian National University(澳大利亚国立大学);École polytechnique fédérale de Lausanne(洛桑联邦理工学院);Data61, CSIRO(澳大利亚联邦科学与工业研究组织数据61);Monash University(莫纳什大学)

Jieming Zhou, Tong Zhang, Pengfei Fang, Lars Petersson, Mehrtash Harandi

摘要:

在引入图神经网络(GNNs)之前,建模和分析不规则数据,特别是图形,被认为是深度学习的致命弱点。GNN的核心概念是通过递归聚合中心节点及其邻居的表示来找到表示。GNN的核心概念是通过递归地聚合中心节点的表示及其邻居的表示来找到表示,并且它的成功已经被许多GNN的设计所证明。然而,大多数算法只注重利用节点与其邻居之间的一阶信息。在本文中,我们通过对GNN的核心操作进行令人沮丧的简单和无辜的修改来引入中心节点置换变量函数,即特征相关性聚集(FOG)模块,该模块从管道中节点与其邻居之间的特征相关性中学习二阶信息。通过将FOG添加到现有的GNN变体中,我们根据经验验证了这种二阶信息在广泛的基准测试中补充了原始GNN生成的特征。一个有形的提升模型的性能被观察到,该模型超过了以前的国家的最先进的结果,同时采用更少的参数显着的利润率。(e.g.,使用图卷积网络的真实世界分子数据集的33.116%的改进)。

英文摘要:

Prior to the introduction of Graph Neural Networks (GNNs), modeling and analyzing irregular data, particularly graphs, was thought to be the Achilles' heel of deep learning. The core concept of GNNs is to find a representation by recursively aggregating the representations of a central node and those of its neighbors. The core concept of GNNs is to find a representation by recursively aggregating the representations of a central node and those of its neighbor, and its success has been demonstrated by many GNNs' designs. However, most of them only focus on using the first-order information between a node and its neighbors. In this paper, we introduce a central node permutation variant function through a frustratingly simple and innocent-looking modification to the core operation of a GNN, namely the Feature cOrrelation aGgregation (FOG) module which learns the second-order information from feature correlation between a node and its neighbors in the pipeline. By adding FOG into existing variants of GNNs, we empirically verify this second-order information complements the features generated by original GNNs across a broad set of benchmarks. A tangible boost in performance of the model is observed where the model surpasses previous state-of-the-art results by a significant margin while employing fewer parameters. (e.g., 33.116% improvement on a real-world molecular dataset using graph convolutional networks).

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。

↑