A Generalization of Convolutional Neural Networks to Graph-Structured Data
arXiv:1704.08165
Abstract
This paper introduces a generalization of Convolutional Neural Networks (CNNs) from low-dimensional grid data, such as images, to graph-structured data. We propose a novel spatial convolution utilizing a random walk to uncover the relations within the input, analogous to the way the standard convolution uses the spatial neighborhood of a pixel on the grid. The convolution has an intuitive interpretation, is efficient and scalable and can also be used on data with varying graph structure. Furthermore, this generalization can be applied to many standard regression or classification problems, by learning the the underlying graph. We empirically demonstrate the performance of the proposed CNN on MNIST, and challenge the state-of-the-art on Merck molecular activity data set.
References in corpus (7)
- Adam: A Method for Stochastic Optimization
- Semi-Supervised Classification with Graph Convolutional Networks
- Geometric deep learning: going beyond Euclidean data
- Spectral Networks and Locally Connected Networks on Graphs
- Deep Convolutional Networks on Graph-Structured Data
- Convolutional Neural Networks for Sentence Classification
- Gated Graph Sequence Neural Networks
Cited by in corpus (10)
- Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
- Graph Neural Networks: Taxonomy, Advances and Trends
- Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks
- Adaptive Filters in Graph Convolutional Neural Networks
- FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation
- Interpretable Crowd Flow Prediction with Spatial-Temporal Self-Attention
- Image Retrieval for Structure-from-Motion via Graph Convolutional Network
- Stochastic encoding of graphs in deep learning allows for complex analysis of gender classification in resting-state and task functional brain networks from the UK Biobank
- Wall Stress Estimation of Cerebral Aneurysm based on Zernike Convolutional Neural Networks
- Prediction of Hereditary Cancers Using Neural Networks