Efficient Unsupervised Graph Embedding With Attributed Graph Reduction and Dual-Level Loss
- 31 July 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (12) , 8120-8134
Abstract
Graph embedding aims to extract low-dimensional representation vectors, commonly referred to as embeddings, from graph data. The generated embeddings simplify subsequent data analysis and machine learning tasks. Recently, researchers have proposed the use of contrastive learning on graphs to extract node embeddings in an unsupervised manner. Although existing graph contrastive learning methods have significantly advanced this field, there is still potential for further exploration, particularly in optimizing training efficiency and enhancing embedding quality . In this paper, we propose an efficient unsupervised graph embedding method named GEARED. First, the method involves an attributed graph reduction module that converts the raw graph into a reduced graph, greatly improving model training efficiency. Second, GEARED employs a dual-level loss with adaptive scaling factors to ensure the acquisition of high-quality embeddings. Finally, we conduct a partial derivative analysis to elucidate the specific mechanisms through which GEARED is capable of generating high-quality embeddings. Extensive experimental evaluations on 14 benchmark datasets show that GEARED consistently outperforms state-of-the-art methods in terms of training efficiency and classification accuracy. For instance, GEARED achieves a training speedup of over 40 times on both the CS and Physics datasets while maintaining superior classification accuracy.Keywords
Funding Information
- National Natural Science Foundation of China (62372264)
- JD.com Inc.
This publication has 51 references indexed in Scilit:
- Fast Unsupervised Graph Embedding via Graph Zoom Learning2023
- Tower Bridge Net (TB-Net): Bidirectional Knowledge Graph Aware Embedding Propagation for Explainable Recommender Systems2022
- Graph coarsening: from scientific computing to machine learningSeMA Journal, 2022
- Understanding the Behaviour of Contrastive Loss2021
- Dynamic Opinion Maximization in Social NetworksIEEE Transactions on Knowledge and Data Engineering, 2021
- Contrastive Multiview Coding2020
- Sub2Vec: Feature Learning for Subgraphs2018
- Comparison of descriptor spaces for chemical compound retrieval and classificationKnowledge and Information Systems, 2007
- Protein function prediction via graph kernelsBioinformatics, 2005
- On the momentum term in gradient descent learning algorithmsNeural Networks, 1999