Task-Specific Prompt with Global Context for Multi-Task Graph Pre-Training

Virgil Qiu, Author 2, Author 3, Author 4, Author 5

graph learningmulti-task learningprompt engineeringtransfer learning

2609.00047

Builder Relevance

80%

2h ago

Abstract

This paper presents TPGC, a dual-prior prompt initialization solution that enhances multi-task graph pre-training by modeling the synergy between task and structural priors.

Reality Card

Core Claim

TPGC achieves consistently better performance in few-shot settings on 6 benchmarks compared to state-of-the-art baselines, with fewer tunable parameters and lower runtime.

Method / Result

TPGC outperforms state-of-the-art baselines on 6 benchmarks under few-shot settings.

Limitations

The reliance on an auxiliary graph for prompt initialization may limit generalizability to other graph structures.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.

← Back to all papers