Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

2-2026

Abstract

Node classification is a fundamental problem in information retrieval with many real-world applications, such as community detection in social networks, grouping articles published online and product categorization in e-commerce. Zero-shot node classification in text-attributed graphs (TAGs) presents a significant challenge, particularly due to the absence of labeled data. In this paper, we propose a novel Zero-shot Prompt Tuning (ZPT) framework to address this problem by leveraging a Universal Bimodal Conditional Generator (UBCG). Our approach begins with pre-training a graph-language model to capture both the graph structure and the associated textual descriptions of each node. Following this, a conditional generative model is trained to learn the joint distribution of nodes in both graph and text modalities, enabling the generation of synthetic samples for each class based solely on the class name. These synthetic node and text embeddings are subsequently used to perform continuous prompt tuning, facilitating effective node classification in a zero-shot setting. Furthermore, we conduct extensive experiments on multiple benchmark datasets, demonstrating that our framework performs better than existing state-of-the-art baselines. We also provide ablation studies to validate the contribution of the bimodal generator.

Keywords

conditional generative model, prompt tuning, text-attributed graphs, zero-shot node classification

Discipline

Databases and Information Systems

Research Areas

Data Science and Engineering

Publication

WSDM '26: Proceedings of the 19th ACM International Conference on Web Search and Data Mining, February 22-26, Boise, ID

First Page

520

Last Page

530

ISBN

9798400722929

Identifier

10.1145/3773966.3777999

Publisher

Association for Computing Machinery

City or Country

New York

Additional URL

https://doi.org/10.1145/3773966.3777999

Download

Share

COinS