arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.01660cs.LGcs.AI
收藏

基于提升的自适应图小波的图神经网络

Graph Neural Networks With Lifting-based Adaptive Graph Wavelets

Shanghai Jiao Tong University(上海交通大学);École Polytechnique Fédérale de Lausanne (EPFL)(洛桑联邦理工学院)

Mingxing Xu, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong, Pascal Frossard

摘要:

基于谱的图神经网络(SGNNs)在图表示学习中受到越来越多的关注。然而,现有的SGNN在实现具有刚性变换的图滤波器(例如,图傅立叶或预定义的图小波变换),并且不能适应驻留在图上的信号和手头的任务。在本文中,我们提出了一类新的图神经网络,实现了自适应图小波图滤波器。具体地,自适应图小波是用神经网络参数化提升结构来学习的,其中结构感知的基于注意力的提升操作(即,预测和更新操作)被开发以联合考虑图结构和节点特征。我们提出了基于扩散小波的提升,以减轻划分非二部图引起的结构信息损失。通过设计,保证了所得到的小波变换的局部性和稀疏性以及提升结构的可扩展性。我们进一步推导出一个软阈值滤波操作,通过学习稀疏图表示的学习小波,产生一个本地化的,高效的,可扩展的基于小波的图形滤波器。为了确保学习的图表示对于节点排列是不变的,在网络的输入处采用层来根据节点的局部拓扑信息对节点进行重新排序。我们在基准引用和生物信息学图数据集上评估了节点级和图级表示学习任务中提出的网络。大量的实验证明了所提出的网络在准确性,效率和可扩展性方面优于现有的SGNN。

英文摘要:

Spectral-based graph neural networks (SGNNs) have been attracting increasing attention in graph representation learning. However, existing SGNNs are limited in implementing graph filters with rigid transforms (e.g., graph Fourier or predefined graph wavelet transforms) and cannot adapt to signals residing on graphs and tasks at hand. In this paper, we propose a novel class of graph neural networks that realizes graph filters with adaptive graph wavelets. Specifically, the adaptive graph wavelets are learned with neural network-parameterized lifting structures, where structure-aware attention-based lifting operations (i.e., prediction and update operations) are developed to jointly consider graph structures and node features. We propose to lift based on diffusion wavelets to alleviate the structural information loss induced by partitioning non-bipartite graphs. By design, the locality and sparsity of the resulting wavelet transform as well as the scalability of the lifting structure are guaranteed. We further derive a soft-thresholding filtering operation by learning sparse graph representations in terms of the learned wavelets, yielding a localized, efficient, and scalable wavelet-based graph filters. To ensure that the learned graph representations are invariant to node permutations, a layer is employed at the input of the networks to reorder the nodes according to their local topology information. We evaluate the proposed networks in both node-level and graph-level representation learning tasks on benchmark citation and bioinformatics graph datasets. Extensive experiments demonstrate the superiority of the proposed networks over existing SGNNs in terms of accuracy, efficiency, and scalability.

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。

↑