Simple Unsupervised Graph Representation Learning
DOI:
https://doi.org/10.1609/aaai.v36i7.20748Keywords:
Machine Learning (ML)Abstract
In this paper, we propose a simple unsupervised graph representation learning method to conduct effective and efficient contrastive learning. Specifically, the proposed multiplet loss explores the complementary information between the structural information and neighbor information to enlarge the inter-class variation, as well as adds an upper bound loss to achieve the finite distance between positive embeddings and anchor embeddings for reducing the intra-class variation. As a result, both enlarging inter-class variation and reducing intra-class variation result in small generalization error, thereby obtaining an effective model. Furthermore, our method removes widely used data augmentation and discriminator from previous graph contrastive learning methods, meanwhile available to output low-dimensional embeddings, leading to an efficient model. Experimental results on various real-world datasets demonstrate the effectiveness and efficiency of our method, compared to state-of-the-art methods. The source codes are released at https://github.com/YujieMo/SUGRL.Downloads
Published
2022-06-28
How to Cite
Mo, Y., Peng, L., Xu, J., Shi, X., & Zhu, X. (2022). Simple Unsupervised Graph Representation Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 36(7), 7797-7805. https://doi.org/10.1609/aaai.v36i7.20748
Issue
Section
AAAI Technical Track on Machine Learning II