Dual-Primal Graph Convolutional Networks

06/03/2018
by   Federico Monti, et al.
0

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.

READ FULL TEXT
10/28/2017

Topology Adaptive Graph Convolutional Networks

Convolution acts as a local feature extractor in convolutional neural ne...
04/04/2019

DAGCN: Dual Attention Graph Convolutional Networks

Graph convolutional networks (GCNs) have recently become one of the most...
06/10/2021

Simple Graph Convolutional Networks

Many neural networks for graphs are based on the graph convolution opera...
01/11/2016

How to learn a graph from smooth signals

We propose a framework that learns the graph structure underlying a set ...
06/04/2019

An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem

This paper introduces a new learning-based approach for approximately so...
04/29/2020

Directed Graph Convolutional Network

Graph Convolutional Networks (GCNs) have been widely used due to their o...
05/30/2019

Quantifying the alignment of graph and features in deep learning

We show that the classification performance of Graph Convolutional Netwo...