GraphMix: Regularized Training of Graph Neural Networks for Semi-Supervised Learning

09/25/2019
by   Vikas Verma, et al.
4

We present GraphMix, a regularization technique for Graph Neural Network based semi-supervised object classification, leveraging the recent advances in the regularization of classical deep neural networks. Specifically, we propose a unified approach in which we train a fully-connected network jointly with the graph neural network via parameter sharing, interpolation-based regularization, and self-predicted-targets. Our proposed method is architecture agnostic in the sense that it can be applied to any variant of graph neural networks which applies a parametric transformation to the features of the graph nodes. Despite its simplicity, with GraphMix we can consistently improve results and achieve or closely match state-of-the-art performance using even simpler architectures such as Graph Convolutional Networks, across three established graph benchmarks: the Cora, Citeseer and Pubmed citation network datasets, as well as three newly proposed datasets : Cora-Full, Co-author-CS and Co-author-Physics.

READ FULL TEXT
research
12/08/2021

Improving the Training of Graph Neural Networks with Consistency Regularization

Graph neural networks (GNNs) have achieved notable success in the semi-s...
research
08/21/2020

Optimization of Graph Neural Networks with Natural Gradient Descent

In this work, we propose to employ information-geometric tools to optimi...
research
03/10/2018

Attention-based Graph Neural Network for Semi-supervised Learning

Recently popularized graph neural networks achieve the state-of-the-art ...
research
05/07/2020

Machine Learning on Graphs: A Model and Comprehensive Taxonomy

There has been a surge of recent interest in learning representations fo...
research
09/29/2021

Adaptive Multi-layer Contrastive Graph Neural Networks

We present Adaptive Multi-layer Contrastive Graph Neural Networks (AMC-G...
research
11/03/2020

Sampling and Recovery of Graph Signals based on Graph Neural Networks

We propose interpretable graph neural networks for sampling and recovery...
research
05/19/2023

GraphFC: Customs Fraud Detection with Label Scarcity

Custom officials across the world encounter huge volumes of transactions...

Please sign up or login with your details

Forgot password? Click here to reset