Deep Convolutional Networks on Graph-Structured Data

Abstract

Deep Learning's recent successes have mostly relied on Convolutional Networks, which exploit fundamental statistical properties of images, sounds and video data: the local stationarity and multi-scale compositional structure, that allows expressing long range interactions in terms of shorter, localized interactions. However, there exist other important examples, such as text documents or bioinformatic data, that may lack some or all of these strong statistical regularities. In this paper we consider the general question of how to construct deep architectures with small learning complexity on general non-Euclidean domains, which are typically unknown and need to be estimated from the data. In particular, we develop an extension of Spectral Networks which incorporates a Graph Estimation procedure, that we test on large-scale classification problems, matching or improving over Dropout Networks with far less parameters to estimate.

References in corpus (1)

• Emergence of Complex-Like Cells in a Temporal Product Network with Local Receptive Fields

Cited by in corpus (25)

• Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
• A simple neural network module for relational reasoning
• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
• Short-term traffic flow forecasting with spatial-temporal correlation in a hybrid deep learning framework
• Adaptive Graph Convolutional Neural Networks
• Covariant Compositional Networks For Learning Graphs
• SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation
• Spectral-based Graph Convolutional Network for Directed Graphs
• Geometric deep learning on graphs and manifolds using mixture model CNNs
• Premise Selection for Theorem Proving by Deep Graph Embedding
• Image Classification with Hierarchical Multigraph Networks
• Graph Convolution: A High-Order and Adaptive Approach
• Inductive Representation Learning in Large Attributed Graphs
• GRASS: Generative Recursive Autoencoders for Shape Structures
• A Framework for Generalizing Graph-based Representation Learning Methods
• Graph Clustering with Dynamic Embedding
• Learning Graph While Training: An Evolving Graph Convolutional Neural Network
• Graph Classification via Deep Learning with Virtual Nodes
• Sparse Diffusion-Convolutional Neural Networks
• DGCNN: Disordered Graph Convolutional Neural Network Based on the Gaussian Mixture Model
• Can GAN Learn Topological Features of a Graph?
• Mesh-based Autoencoders for Localized Deformation Component Analysis
• Tackling Graphical NLP problems with Graph Recurrent Networks
• Intrinsic Geometric Information Transfer Learning on Multiple Graph-Structured Datasets