Dual-Primal Graph Convolutional Networks

by   Federico Monti, et al.

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.


Topology Adaptive Graph Convolutional Networks

Convolution acts as a local feature extractor in convolutional neural ne...

DAGCN: Dual Attention Graph Convolutional Networks

Graph convolutional networks (GCNs) have recently become one of the most...

Simple Graph Convolutional Networks

Many neural networks for graphs are based on the graph convolution opera...

Graph Embedding for Recommendation against Attribute Inference Attacks

In recent years, recommender systems play a pivotal role in helping user...

An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem

This paper introduces a new learning-based approach for approximately so...

How to learn a graph from smooth signals

We propose a framework that learns the graph structure underlying a set ...

Isometric Transformation Invariant and Equivariant Graph Convolutional Networks

Graphs correspond to one of the most important data structures used to r...

Please sign up or login with your details

Forgot password? Click here to reset