Exploiting Text Semantics for Few and Zero Shot Node Classification on Text-attributed Graph

Wang, Yuxiang; Yan, Xiao; Jin, Shiyu; Xu, Quanqing; Hu, Chuang; Zhu, Yuanyuan; Du, Bo; Wu, Jia; Jiang, Jiawei

doi:10.24963/ijcai.2025/385

Exploiting Text Semantics for Few and Zero Shot Node Classification on Text-attributed Graph

Yuxiang Wang, Xiao Yan, Shiyu Jin, Quanqing Xu, Chuang Hu, Yuanyuan Zhu, Bo Du, Jia Wu, Jiawei Jiang

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 3462-3470.

https://doi.org/10.24963/ijcai.2025/385

Keywords

Data Mining: DM: Mining graphs
Machine Learning: ML: Few-shot learning
Machine Learning: ML: Multi-modal learning

Abstract

Text-attributed graph (TAG) provides a text description for each graph node, and few- and zero-shot node classification on TAGs have many applications in fields such as academia and social networks. Existing work utilizes various graph-based augmentation techniques to train the node and text embeddings, while text-based augmentations are largely unexplored. In this paper, we propose Text Semantics Augmentation (TSA) to improve accuracy by introducing more text semantic supervision signals. Specifically, we design two augmentation techniques, i.e., positive semantics matching and negative semantics contrast, to provide more reference texts for each graph node or text description. Positive semantic matching retrieves texts with similar embeddings to match with a graph node. Negative semantic contrast adds a negative prompt to construct a text description with the opposite semantics, which is contrasted with the original node and text. We evaluate TSA on 5 datasets and compare with 13 state-of-the-art baselines. The results show that TSA consistently outperforms all baselines, and its accuracy improvements over the best-performing baseline are usually over 5%. The code is at https://github.com/wyx11112/TSA.

Yuxiang Wang, Xiao Yan, Shiyu Jin, Quanqing Xu, Chuang Hu, Yuanyuan Zhu, Bo Du, Jia Wu, and Jiawei Jiang. 2025. Exploiting Text Semantics for Few and Zero Shot Node Classification on Text-attributed Graph. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 3462–3470. https://doi.org/10.24963/ijcai.2025/385

@inproceedings{ijcai2025p385,
  title     = {Exploiting Text Semantics for Few and Zero Shot Node Classification on Text-attributed Graph},
  author    = {Wang, Yuxiang and Yan, Xiao and Jin, Shiyu and Xu, Quanqing and Hu, Chuang and Zhu, Yuanyuan and Du, Bo and Wu, Jia and Jiang, Jiawei},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {3462--3470},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/385},
  url       = {https://doi.org/10.24963/ijcai.2025/385},
}

TY  - CPAPER
TI  - Exploiting Text Semantics for Few and Zero Shot Node Classification on Text-attributed Graph
AU  - Wang, Yuxiang
AU  - Yan, Xiao
AU  - Jin, Shiyu
AU  - Xu, Quanqing
AU  - Hu, Chuang
AU  - Zhu, Yuanyuan
AU  - Du, Bo
AU  - Wu, Jia
AU  - Jiang, Jiawei
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 3462
EP  - 3470
DO  - 10.24963/ijcai.2025/385
UR  - https://doi.org/10.24963/ijcai.2025/385
ER  -