N-GCN: Multi-scale Graph Convolution for Semi-supervised Node Classification

02/24/2018
by   Sami Abu-El-Haija, et al.
0

Graph Convolutional Networks (GCNs) have shown significant improvements in semi-supervised learning on graph-structured data. Concurrently, unsupervised learning of graph embeddings has benefited from the information contained in random walks. In this paper, we propose a model: Network of GCNs (N-GCN), which marries these two lines of work. At its core, N-GCN trains multiple instances of GCNs over node pairs discovered at different distances in random walks, and learns a combination of the instance outputs which optimizes the classification objective. Our experiments show that our proposed N-GCN model improves state-of-the-art baselines on all of the challenging node classification tasks we consider: Cora, Citeseer, Pubmed, and PPI. In addition, our proposed method has other desirable properties, including generalization to recently proposed semi-supervised learning methods such as GraphSAGE, allowing us to propose N-SAGE, and resilience to adversarial input perturbations.

READ FULL TEXT

page 3

page 7

research
09/26/2018

Every Node Counts: Self-Ensembling Graph Convolutional Networks for Semi-Supervised Learning

Graph convolutional network (GCN) provides a powerful means for graph-ba...
research
06/22/2020

Connecting Graph Convolutional Networks and Graph-Regularized PCA

Graph convolution operator of the GCN model is originally motivated from...
research
04/23/2019

Exploring Graph Learning for Semi-Supervised Classification Beyond Euclidean Data

Semi-supervised classification on graph-structured data has received inc...
research
02/28/2022

ESW Edge-Weights : Ensemble Stochastic Watershed Edge-Weights for Hyperspectral Image Classification

Hyperspectral image (HSI) classification is a topic of active research. ...
research
09/04/2020

LFGCN: Levitating over Graphs with Levy Flights

Due to high utility in many applications, from social networks to blockc...
research
07/12/2019

Semi-Supervised Graph Embedding for Multi-Label Graph Node Classification

The graph convolution network (GCN) is a widely-used facility to realize...
research
10/23/2020

Online Semi-Supervised Learning with Bandit Feedback

We formulate a new problem at the intersectionof semi-supervised learnin...

Please sign up or login with your details

Forgot password? Click here to reset