arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.07028stat.MLcs.LG
收藏

基于潜在固定数据结构的图的非局部特征聚合

Non-Local Feature Aggregation on Graphs via Latent Fixed Data Structures

Baidu Research（百度研究院）

Mostafa Rahmani, Rasoul Shafipour, Ping Li

备注：
published in 2021 IEEE Asilomar Conference on Signals, Systems, and Computers
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

摘要：

与图像/文本数据相比，其顺序可以用于使用池化层以直接的方式执行非局部特征聚合，图缺乏张量表示，并且大多数情况下使用逐元素的最大值/均值函数来聚合局部提取的特征向量。在本文中，我们提出了一种新的方法，在图神经网络（GNNs），利用潜在的固定数据结构（LFDS）的全局特征聚合提取的特征向量。局部提取的特征向量被排序/分布在LFDS上，并且利用潜在神经网络（CNN/GNN）来在LFDS上执行特征聚合。该方法被用来设计几种新的全局特征聚合方法的基础上选择的LFDS。我们介绍了多个LFDS，包括循环，三维张量（图像），序列，数据驱动图和一个算法，排序/分配的LFDS上提取的局部特征向量。虽然所提出的方法的计算复杂度是线性的输入图的顺序，他们取得竞争力或更好的结果。

英文摘要：

In contrast to image/text data whose order can be used to perform non-local feature aggregation in a straightforward way using the pooling layers, graphs lack the tensor representation and mostly the element-wise max/mean function is utilized to aggregate the locally extracted feature vectors. In this paper, we present a novel approach for global feature aggregation in Graph Neural Networks (GNNs) which utilizes a Latent Fixed Data Structure (LFDS) to aggregate the extracted feature vectors. The locally extracted feature vectors are sorted/distributed on the LFDS and a latent neural network (CNN/GNN) is utilized to perform feature aggregation on the LFDS. The proposed approach is used to design several novel global feature aggregation methods based on the choice of the LFDS. We introduce multiple LFDSs including loop, 3D tensor (image), sequence, data driven graphs and an algorithm which sorts/distributes the extracted local feature vectors on the LFDS. While the computational complexity of the proposed methods are linear with the order of input graphs, they achieve competitive or better 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。

↑