TAGA: Text-Attributed Graph Self-Supervised Learning by Synergizing Graph and Text Mutual Transformations
Open Access
- 10 November 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 4263-4272
Abstract
No abstract availableFunding Information
- NSF (National Science Foundation) (2007716, 2007976, 1942594, 1907805)
- Cisco Faculty Research Award
- NIH (National Institutes of Health) (R01AG089806)
This publication has 8 references indexed in Scilit:
- Text-Attributed Graph Representation Learning: Methods, Applications, and Challenges2024
- Exploring the Potential of Large Language Models (LLMs)in Learning on GraphsACM SIGKDD Explorations Newsletter, 2024
- Augmenting Low-Resource Text Classification with Graph-Grounded Pre-training and Prompting2023
- Eliciting Structural and Semantic Global Knowledge in Unsupervised Graph Contrastive LearningProceedings of the AAAI Conference on Artificial Intelligence, 2023
- GraphMAE: Self-Supervised Masked Graph Autoencoders2022
- A Survey of Machine Learning for Computer Architecture and SystemsACM Computing Surveys, 2022
- InfraNodus: Generating Insight Using Text Network Analysis2019
- Full‐text citation analysis: A new method to enhance scholarly networksJournal of the American Society for Information Science and Technology, 2013