Automated Graph Learning via Population Based Self-Tuning GCN

07/09/2021
by   Ronghang Zhu, et al.
0

Owing to the remarkable capability of extracting effective graph embeddings, graph convolutional network (GCN) and its variants have been successfully applied to a broad range of tasks, such as node classification, link prediction, and graph classification. Traditional GCN models suffer from the issues of overfitting and oversmoothing, while some recent techniques like DropEdge could alleviate these issues and thus enable the development of deep GCN. However, training GCN models is non-trivial, as it is sensitive to the choice of hyperparameters such as dropout rate and learning weight decay, especially for deep GCN models. In this paper, we aim to automate the training of GCN models through hyperparameter optimization. To be specific, we propose a self-tuning GCN approach with an alternate training algorithm, and further extend our approach by incorporating the population based training scheme. Experimental results on three benchmark datasets demonstrate the effectiveness of our approaches on optimizing multi-layer GCN, compared with several representative baselines.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/05/2021

Label-GCN: An Effective Method for Adding Label Propagation to Graph Convolutional Networks

We show that a modification of the first layer of a Graph Convolutional ...
research
05/12/2019

On Graph Classification Networks, Datasets and Baselines

Graph classification receives a great deal of attention from the non-Euc...
research
04/03/2020

Attribute2vec: Deep Network Embedding Through Multi-Filtering GCN

We present a multi-filtering Graph Convolution Neural Network (GCN) fram...
research
12/17/2021

Community-based Layerwise Distributed Training of Graph Convolutional Networks

The Graph Convolutional Network (GCN) has been successfully applied to m...
research
02/11/2021

Quartile-based Prediction of Event Types and Event Time in Business Processes using Deep Learning

Deep learning models are now being increasingly used for predictive proc...
research
07/03/2023

Node-weighted Graph Convolutional Network for Depression Detection in Transcribed Clinical Interviews

We propose a simple approach for weighting self-connecting edges in a Gr...
research
12/18/2021

GCN-Geo: A Graph Convolution Network-based Fine-grained IP Geolocation Framework

Classical fine-grained measurement-based IP geolocation algorithms often...

Please sign up or login with your details

Forgot password? Click here to reset