Dual-Primal Graph Convolutional Networks
arXiv:1806.00770
Abstract
In recent years, there has been a surge of interest in developing deep learning methods for non-Euclidean structured data such as graphs. In this paper, we propose Dual-Primal Graph CNN, a graph convolutional architecture that alternates convolution-like operations on the graph and its dual. Our approach allows to learn both vertex- and edge features and generalizes the previous graph attention (GAT) model. We provide extensive experimental validation showing state-of-the-art results on a variety of tasks tested on established graph benchmarks, including CORA and Citeseer citation networks as well as MovieLens, Flixter, Douban and Yahoo Music graph-guided recommender systems.
References in corpus (13)
- Neural Machine Translation by Jointly Learning to Align and Translate
- Semi-Supervised Classification with Graph Convolutional Networks
- Inductive Representation Learning on Large Graphs
- Neural Message Passing for Quantum Chemistry
- Spectral Networks and Locally Connected Networks on Graphs
- Modeling polypharmacy side effects with graph convolutional networks
- Deep Convolutional Networks on Graph-Structured Data
- Higher-order organization of complex networks
- Dynamic Graph CNN for Learning on Point Clouds
- Learning shape correspondence with anisotropic convolutional neural networks
- Matrix Completion on Graphs
- Provable Inductive Matrix Completion
- A Convolutional Encoder Model for Neural Machine Translation
Cited by in corpus (20)
- MeshCNN: A Network with an Edge
- HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs
- Fake News Detection on Social Media using Geometric Deep Learning
- Composition-based Multi-Relational Graph Convolutional Networks
- Subdivision-Based Mesh Convolution Networks
- Relational Graph Attention Networks
- Differentiable Graph Module (DGM) for Graph Convolutional Networks
- Primal-Dual Mesh Convolutional Neural Networks
- Line Hypergraph Convolution Network: Applying Graph Convolution for Hypergraphs
- Provably Powerful Graph Networks
- Edge Representation Learning with Hypergraphs
- Graph Neural Networks for IceCube Signal Classification
- Bayesian Graph Convolutional Neural Networks using Node Copying
- Bayesian Graph Convolutional Neural Networks Using Non-Parametric Graph Learning
- Learning Color Compatibility in Fashion Outfits
- Beyond Node Embedding: A Direct Unsupervised Edge Representation Framework for Homogeneous Networks
- Dimensional Reweighting Graph Convolutional Networks
- An Industry Evaluation of Embedding-based Entity Alignment
- GraphSeam: Supervised Graph Learning Framework for Semantic UV Mapping
- Multi-modal Entity Alignment in Hyperbolic Space