Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networks
Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networks
复制标题
DOI：
10.1145/3627816
复制
发表时间：
2021-07
影响因子：
16.6
通讯作者：
Zhiqian Chen;Fanglan Chen;Lei Zhang;Taoran Ji;Kaiqun Fu;Liang Zhao;Feng Chen;Lingfei Wu;
中科院分区：
文献类型：
--
作者：
Zhiqian Chen;Fanglan Chen;Lei Zhang;Taoran Ji;Kaiqun Fu;Liang Zhao;Feng Chen;Lingfei Wu;
深度学习的性能最近得到了广泛的认可。图神经网络（GNN）旨在处理经典深度学习不容易管理的图结构数据。由于大多数GNN都是使用不同的理论创建的，因此直接比较是不可能的。以前的研究主要集中在对现有模型进行分类，很少关注它们的内在联系。本研究的目的是建立一个统一的框架，集成基于谱图和近似理论的GNNs。该框架整合了基于空间和频谱的GNN之间的强大集成，同时将每个领域内存在的方法紧密关联。
Deep learning’s performance has been extensively recognized recently. Graph neural networks (GNNs) are designed to deal with graph-structural data that classical deep learning does not easily manage. Since most GNNs were created using distinct theories, direct comparisons are impossible. Prior research has primarily concentrated on categorizing existing models, with little attention paid to their intrinsic connections. The purpose of this study is to establish a unified framework that integrates GNNs based on spectral graph and approximation theory. The framework incorporates a strong integration between spatial- and spectral-based GNNs while tightly associating approaches that exist within each respective domain.