Skip to content
AI News HubLIVE
Original source2 min read

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

Summary

The paper proposes TPGC, a dual-prior prompt initialization method for multi-task graph pre-training. Its Task-Prior Injection Module and Structure-Prior Injection Module let prompts inherit optimization preferences from multi-task pre-training and transferable global structural context from an auxiliary graph. Across six benchmarks, TPGC outperforms state-of-the-art baselines in few-shot settings with fewer tunable parameters and lower runtime.

SourcearXiv Machine LearningAuthor: Zhiyang Qiu, Yangtao Wang, Xiaocui Li, Yanzhao Xie, Siyuan Chen, Wensheng Zhang
Task-Specific Prompt with Global Context for Multi-Task Graph Pre-Training
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 30 Aug 2026]

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

View a PDF of the paper titled Task-Specific Prompt with Global Context for Multi-Task Graph Pre-Training, by Zhiyang Qiu and 5 other authors

View PDF HTML (experimental)

Abstract:Graph prompt learning is an effective paradigm to adapt pre-trained graph models to downstream tasks in low-resource scenarios. However, existing multi-task graph pre-training frameworks generally use randomly initialized prompts, leading to poor alignment between the prompt space, pretext objectives and graph structural characteristics. This greatly weakens the task relevance, structural awareness and transferability of prompt representations. To address this challenge, we propose TPGC, a dual-prior prompt initialization solution that explicitly models the synergy between task prior and structural prior. Specifically, the Task-Prior Injection Module first conducts a short homologous multi-task pre-training on an auxiliary graph, enabling prompt initialization to inherit optimization preferences associated with multiple pretext tasks. Built on the task-aware representations, the Structure-Prior Injection Module further extracts transferable global structural context from the auxiliary graph, converting it into layer-wise prompt vectors by aggregating structurally informative node embeddings. Extensive experiments on 6 mainstream benchmarks covering node and graph classification show that TPGC achieves consistently better performance under few-shot settings than state-of-the-art baselines, with fewer downstream tunable parameters and lower runtime. The code is available at this https URL

Comments: 16 pages, 6 figures

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

Cite as: arXiv:2609.00047 [cs.LG]

(or arXiv:2609.00047v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2609.00047

arXiv-issued DOI via DataCite

Submission history

From: Yangtao Wang [view email] [v1] Sun, 30 Aug 2026 04:28:51 UTC (510 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Task-Specific Prompt with Global Context for Multi-Task Graph Pre-Training, by Zhiyang Qiu and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-09

Change to browse by:

cs cs.AI

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • TPGC initializes prompts with a task prior via short homologous multi-task pre-training on an auxiliary graph.
  • A structure-prior module converts global structural context into layer-wise prompt vectors.
  • TPGC consistently beats state-of-the-art baselines on six node and graph classification benchmarks in few-shot settings.
  • The method uses fewer downstream tunable parameters and has lower runtime.

Highlights and analysis are generated automatically and may contain errors. Check the original source.