Freeze, Prompt, and Adapt: A Framework for Source-free Unsupervised GNN Prompting

ICLR 2026 Conference Submission21218 Authors

Keywords: Graph Neural Networks, Prompting, Unsupervised

Abstract:

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 co-variate 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.

Primary Area: learning on graphs and other geometries & topologies

Submission Number: 21218