Adaptive Multi-layer Contrastive Graph Neural Networks

09/29/2021
by   Shuhao Shi, et al.
0

We present Adaptive Multi-layer Contrastive Graph Neural Networks (AMC-GNN), a self-supervised learning framework for Graph Neural Network, which learns feature representations of sample data without data labels. AMC-GNN generates two graph views by data augmentation and compares different layers' output embeddings of Graph Neural Network encoders to obtain feature representations, which could be used for downstream tasks. AMC-GNN could learn the importance weights of embeddings in different layers adaptively through the attention mechanism, and an auxiliary encoder is introduced to train graph contrastive encoders better. The accuracy is improved by maximizing the representation's consistency of positive pairs in the early layers and the final embedding space. Our experiments show that the results can be consistently improved by using the AMC-GNN framework, across four established graph benchmarks: Cora, Citeseer, Pubmed, DBLP citation network datasets, as well as four newly proposed datasets: Co-author-CS, Co-author-Physics, Amazon-Computers, Amazon-Photo.

READ FULL TEXT
research
09/25/2019

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

We present GraphMix, a regularization technique for Graph Neural Network...
research
06/12/2020

Weisfeiler-Lehman Embedding for Molecular Graph Neural Networks

A graph neural network (GNN) is a good choice for predicting the chemica...
research
05/01/2023

A Simplified Framework for Contrastive Learning for Node Representations

Contrastive learning has recently established itself as a powerful self-...
research
09/02/2022

A Novel Approach for Pill-Prescription Matching with GNN Assistance and Contrastive Learning

Medication mistaking is one of the risks that can result in unpredictabl...
research
09/15/2021

Learning Robot Structure and Motion Embeddings using Graph Neural Networks

We propose a learning framework to find the representation of a robot's ...
research
05/04/2023

Revisiting Graph Contrastive Learning for Anomaly Detection

Combining Graph neural networks (GNNs) with contrastive learning for ano...
research
02/12/2023

USER: Unsupervised Structural Entropy-based Robust Graph Neural Network

Unsupervised/self-supervised graph neural networks (GNN) are vulnerable ...

Please sign up or login with your details

Forgot password? Click here to reset