Geometric deep learning on graphs and manifolds using mixture model CNNs

Abstract

Deep learning has achieved a remarkable performance breakthrough in several fields, most notably in speech recognition, natural language processing, and computer vision. In particular, convolutional neural network (CNN) architectures currently produce state-of-the-art performance on a variety of image analysis tasks such as object detection and recognition. Most of deep learning research has so far focused on dealing with 1D, 2D, or 3D Euclidean-structured data such as acoustic signals, images, or videos. Recently, there has been an increasing interest in geometric deep learning, attempting to generalize deep learning methods to non-Euclidean structured data such as graphs and manifolds, with a variety of applications from the domains of network analysis, computational social science, or computer graphics. In this paper, we propose a unified framework allowing to generalize CNN architectures to non-Euclidean domains (graphs and manifolds) and learn local, stationary, and compositional task-specific features. We show that various non-Euclidean CNN methods previously proposed in the literature can be considered as particular instances of our framework. We test the proposed method on standard tasks from the realms of image-, graph- and 3D shape analysis and show that it consistently outperforms previous approaches.

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Semi-Supervised Classification with Graph Convolutional Networks
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Geometric deep learning: going beyond Euclidean data
• Spectral Networks and Locally Connected Networks on Graphs
• Deep Convolutional Networks on Graph-Structured Data
• Learning Multiagent Communication with Backpropagation
• Learning shape correspondence with anisotropic convolutional neural networks
• Matrix Completion on Graphs
• Fast Robust PCA on Graphs
• Robust Principal Component Analysis on Graphs
• Bayesian Inference of Bijective Non-Rigid Shape Correspondence

Cited by in corpus (21)

• Adversarial Attacks on Neural Networks for Graph Data
• DeeperGCN: All You Need to Train Deeper GCNs
• Residual Gated Graph ConvNets
• SIGN: Scalable Inception Graph Neural Networks
• Temporal Graph Networks for Deep Learning on Dynamic Graphs
• Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphs
• Reasoning Visual Dialogs with Structural and Partial Observations
• Understanding GNN Computational Graph: A Coordinated Computation, IO, and Memory Perspective
• Pointwise Rotation-Invariant Network with Adaptive Sampling and 3D Spherical Voxel Convolution
• Single Image 3D Hand Reconstruction with Mesh Convolutions
• Context-Aware Visual Compatibility Prediction
• Topological based classification of paper domains using graph convolutional networks
• Get Rid of Suspended Animation Problem: Deep Diffusive Neural Network on Graph Semi-Supervised Classification
• Recovering Geometric Information with Learned Texture Perturbations
• Towards Time-Aware Context-Aware Deep Trust Prediction in Online Social Networks
• Sparse hierarchical representation learning on molecular graphs
• G5: A Universal GRAPH-BERT for Graph-to-Graph Transfer and Apocalypse Learning
• Characters as Graphs: Recognizing Online Handwritten Chinese Characters via Spatial Graph Convolutional Network
• Learning Chebyshev Basis in Graph Convolutional Networks for Skeleton-based Action Recognition
• Lookup subnet based Spatial Graph Convolutional neural Network
• OmniLayout: Room Layout Reconstruction from Indoor Spherical Panoramas