无需标签和源数据，让预训练图神经网络在无监督下高效适配新任务。
Freeze, Prompt, and Adapt: A Framework for Source-free Unsupervised GNN Prompting
- 冻结预训练模型，通过伪标签与一致性正则化训练提示函数。
- 在无标签目标域上性能超越有标签的监督方法，解决分布偏移问题。
- 适合资源受限场景，尤其适用于隐私敏感或数据不可得的部署环境。
提示调优已成为将预训练图神经网络（GNN）适配到下游任务的关键机制。然而，现有方法多依赖标注数据优化提示参数，并通常微调特定任务的预测头，这削弱了参数高效适配的潜力。本文提出无监督图提示问题（UGPP），一个新挑战性设定：预训练GNN完全冻结，目标域无标签，源数据不可访问，且目标分布存在协变量偏移。为此，我们提出首个完全无监督的GNN提示框架UGPrompt。该框架利用一致性正则化和伪标签训练提示函数，结合多样性和领域正则化缓解类别不平衡与分布差异。大量实验表明，UGPrompt在无标签条件下持续优于具备标签数据的先进监督提示方法，验证了无监督提示作为实际适配范式的可行性。
原文摘要 · Abstract (English)
Prompt tuning has become a key mechanism for adapting pre-trained Graph Neural Networks (GNNs) to new downstream tasks. However, existing approaches are predominantly supervised, relying on labeled data to optimize the prompting parameters and typically fine-tuning a task-specific prediction head -- practices that undermine the promise of parameter-efficient adaptation. We propose Unsupervised Graph Prompting Problem (UGPP), a challenging new setting where the pre-trained GNN is kept entirely frozen, labels on the target domain are unavailable, the source data is inaccessible, and the target distribution exhibits covariate shift. To address this, we propose UGPrompt, the first fully unsupervised GNN prompting framework. UGPrompt leverages consistency regularization and pseudo-labeling to train a prompting function, complemented with diversity and domain regularization to mitigate class imbalance and distribution mismatch. Our extensive experiments demonstrate that UGPrompt consistently outperforms state-of-the-art supervised prompting methods with access to labeled data, demonstrating the viability of unsupervised prompting as a practical adaptation paradigm for GNNs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。