@inproceedings{li-etal-2025-graph-neural,
    title = "Can Graph Neural Networks Learn Language with Extremely Weak Text Supervision?",
    author = "Li, Zihao  and
      Zheng, Lecheng  and
      Jin, Bowen  and
      Fu, Dongqi  and
      Jing, Baoyu  and
      Ban, Yikun  and
      He, Jingrui  and
      Han, Jiawei",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.545/",
    pages = "11138--11165",
    ISBN = "979-8-89176-251-0",
    abstract = "While great success has been achieved in building vision models with Contrastive Language-Image Pre-training (CLIP) over Internet-scale image-text pairs, building transferable Graph Neural Networks (GNNs) with CLIP pipeline is challenging because of the scarcity of labeled data and text supervision, different levels of downstream tasks, and the conceptual gaps between domains. In this work, to address these issues, we propose a multi-modal prompt learning paradigm to effectively adapt pre-trained GNN to downstream tasks and data, given only a few semantically labeled samples, each with extremely weak text supervision. Our new paradigm embeds the graphs directly in the same space as the Large Language Models (LLMs) by learning both graph prompts and text prompts simultaneously. We demonstrate the superior performance of our paradigm in few-shot, multi-task-level, and cross-domain settings. Moreover, we build the first CLIP-style zero-shot classification prototype that can generalize GNNs to unseen classes with extremely weak text supervision."
}