Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
Graph neural networks have become one of the most important techniques to solve machine learning problems on graph-structured data. Recent work on vertex classification proposed deep and distributed learning models to achieve high performance and scalability. However, we find that the feature vectors of benchmark datasets are already quite informative for the classification task, and the graph structure only provides a means to denoise the data. In this paper, we develop a theoretical framework based on graph signal processing for analyzing graph neural networks. Our results indicate that graph neural networks only perform low-pass filtering on feature vectors and do not have the non-linear manifold learning property. We further investigate their resilience to feature noise and propose some insights on GCN-based graph neural network design.
Code (2)
Tasks
AllGeneral ClassificationGraph Neural NetworkMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Revisiting 3D Reconstruction Kernels as Low-Pass Filters
3D reconstruction is to recover 3D signals from the sampled discrete 2D pixels, with the goal to converge continuous 3D spaces. In this paper, we revisit 3D reconstruction from the perspective of signal processing, ident…
3D ReconstructionRevisiting $Ψ$DONet: microlocally inspired filters for incomplete-data tomographic reconstructions
In this paper, we revisit a supervised learning approach based on unrolling, known as $\Psi$DONet, by providing a deeper microlocal interpretation for its theoretical analysis, and extending its study to the case of spar…
Tomographic ReconstructionsA User Guide to Low-Pass Graph Signal Processing and its Applications
The notion of graph filters can be used to define generative models for graph data. In fact, the data obtained from many examples of network dynamics may be viewed as the output of a graph filter. With this interpretatio…
Beyond Low-pass Filtering: Graph Convolutional Networks with Automatic Filtering
Graph convolutional networks are becoming indispensable for deep learning from graph-structured data. Most of the existing graph convolutional networks share two big shortcomings. First, they are essentially low-pass fil…
Graph Information Matters: Understanding Graph Filters from Interaction Probability
Graph Neural Networks (GNNs) have received extensive affirmation for their promising performance in graph learning problems. Despite their various neural architectures, most are intrinsically graph filters that provide t…
Graph LearningNode Classification