SGPT: Few-Shot Prompt Tuning for Signed Graphs
Zian Zhai, Sima Qing, Xiaoyang Wang, Wenjie Zhang

TL;DR
This paper introduces SGPT, a novel prompt tuning framework that adapts pre-trained unsigned GNNs to signed graph tasks with limited labels, significantly improving performance across multiple benchmarks.
Contribution
SGPT presents a new graph prompting approach using graph and task templates to effectively transfer knowledge from unsigned to signed graphs in few-shot scenarios.
Findings
SGPT outperforms state-of-the-art methods on seven signed graph datasets.
The graph template based on balance theory effectively mitigates structural mismatches.
Task reformulation into link prediction aligns objectives with pre-training.
Abstract
Signed Graph Neural Networks (SGNNs) are effective in learning expressive representations for signed graphs but typically require substantial task-specific labels, limiting their applicability in label-scarce industrial scenarios. In contrast, unsigned graph structures are abundant and can be readily leveraged to pre-train Graph Neural Networks (GNNs), offering a promising solution to reduce supervision requirements in downstream signed graph tasks. However, transferring knowledge from unsigned to signed graphs is non-trivial due to the fundamental discrepancies in graph types and task objectives between pre-training and downstream phases. To address this challenge, we propose Signed Graph Prompt Tuning (SGPT), a novel graph prompting framework that adapts pre-trained unsigned GNNs to few-shot signed graph tasks. We first design a graph template based on balance theory to disentangle…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Graph Neural Networks
