Can I read ARIEL: Adversarial Graph Contrastive Learning on EtoBox?

ARIEL: Adversarial Graph Contrastive Learning by Feng, Shengyu; Jing, Baoyu; Zhu, Yada; Tong, Hanghang is a scholarly article available to read on EtoBox.

What is ARIEL: Adversarial Graph Contrastive Learning about?

Contrastive learning is an effective unsupervised method in graph representation learning, and the key component of contrastive learning lies in the construction of positive and negative samples. Previous methods usually utilize the proximity of nodes in the graph as the principle. Recently, the data-augmentation-based contrastive learning method has advanced to show great power in the visual domain, and some works extended this method from images to graphs. However, unlike the data augmentation on images, the data augmentation on graphs is far less intuitive and much harder to provide high-quality contrastive samples, which leaves much space for improvement. In this work, by introducing an adversarial graph view for data augmentation, we propose a simple but effective method, Adversarial Graph Contrastive Learning (ARIEL), to extract informative contrastive samples within reasonable constraints. We develop a new technique called information regularization for stable training and use subgraph sampling for scalability. We generalize our method from node-level contrastive learning to the graph level by treating each graph instance as a super-node. ARIEL consistently outperforms the c

Author

Feng, Shengyu; Jing, Baoyu; Zhu, Yada; Tong, Hanghang

Published

2022

Language

EN