Robust Spatial Filtering with Graph Convolutional Neural Networks

Abstract

Convolutional Neural Networks (CNNs) have recently led to incredible breakthroughs on a variety of pattern recognition problems. Banks of finite impulse response filters are learned on a hierarchy of layers, each contributing more abstract information than the previous layer. The simplicity and elegance of the convolutional filtering process makes them perfect for structured problems such as image, video, or voice, where vertices are homogeneous in the sense of number, location, and strength of neighbors. The vast majority of classification problems, for example in the pharmaceutical, homeland security, and financial domains are unstructured. As these problems are formulated into unstructured graphs, the heterogeneity of these problems, such as number of vertices, number of connections per vertex, and edge strength, cannot be tackled with standard convolutional techniques. We propose a novel neural learning framework that is capable of handling both homogeneous and heterogeneous data, while retaining the benefits of traditional CNN successes. Recently, researchers have proposed variations of CNNs that can handle graph data. In an effort to create learnable filter banks of graphs, these methods either induce constraints on the data or require preprocessing. As opposed to spectral methods, our framework, which we term Graph-CNNs, defines filters as polynomials of functions of the graph adjacency matrix. Graph-CNNs can handle both heterogeneous and homogeneous graph data, including graphs having entirely different vertex or edge sets. We perform experiments to validate the applicability of Graph-CNNs to a variety of structured and unstructured classification problems and demonstrate state-of-the-art results on document and molecule classification problems.

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Geometric deep learning: going beyond Euclidean data
• Discrete Signal Processing on Graphs
• Deep Convolutional Networks on Graph-Structured Data
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

Cited by in corpus (30)

• A Comprehensive Survey on Graph Neural Networks
• MeshCNN: A Network with an Edge
• EEG based Emotion Recognition: A Tutorial and Review
• Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks
• Attention-based Graph Neural Network for Semi-supervised Learning
• Graph Neural Networks: Taxonomy, Advances and Trends
• A Survey on Graph-Based Deep Learning for Computational Histopathology
• Graph convolutional neural networks as "general-purpose" property predictors: the universality and limits of applicability
• Path Integral Based Convolution and Pooling for Graph Neural Networks
• Motif-based Convolutional Neural Network on Graphs
• Visualization for Histopathology Images using Graph Convolutional Neural Networks
• PAN: Path Integral Based Convolution for Deep Graph Neural Networks
• Walk-Steered Convolution for Graph Classification
• Joint Time-Vertex Fractional Fourier Transform
• Bayesian Graph Convolutional Neural Networks using Node Copying
• Stability and Generalization of Graph Convolutional Neural Networks
• Adaptively Connected Neural Networks
• Bayesian Graph Convolutional Neural Networks Using Non-Parametric Graph Learning
• End-to-End Hierarchical Relation Extraction for Generic Form Understanding
• Graph2Seq: Scalable Learning Dynamics for Graphs
• Histographs: Graphs in Histopathology
• Some New Layer Architectures for Graph CNN
• GFCN: A New Graph Convolutional Network Based on Parallel Flows
• Graph-Based Method for Anomaly Prediction in Brain Network
• Multifold Acceleration of Diffusion MRI via Slice-Interleaved Diffusion Encoding (SIDE)
• Stability and Generalization of Hypergraph Collaborative Networks
• DeGNN: Characterizing and Improving Graph Neural Networks with Graph Decomposition
• Fractional order graph neural network
• 3D Meta Point Signature: Learning to Learn 3D Point Signature for 3D Dense Shape Correspondence
• Weisfeiler and Leman go Hyperbolic: Learning Distance Preserving Node Representations