GMoPE:A Prompt-Expert Mixture Framework for Graph Foundation Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Zhibin, Zhang, Zhixing, Wang, Shuqi, Xie, Xuanting, Kang, Zhao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908629974646784
author Wang, Zhibin
Zhang, Zhixing
Wang, Shuqi
Xie, Xuanting
Kang, Zhao
author_facet Wang, Zhibin
Zhang, Zhixing
Wang, Shuqi
Xie, Xuanting
Kang, Zhao
contents Graph Neural Networks (GNNs) have demonstrated impressive performance on task-specific benchmarks, yet their ability to generalize across diverse domains and tasks remains limited. Existing approaches often struggle with negative transfer, scalability issues, and high adaptation costs. To address these challenges, we propose GMoPE (Graph Mixture of Prompt-Experts), a novel framework that seamlessly integrates the Mixture-of-Experts (MoE) architecture with prompt-based learning for graphs. GMoPE leverages expert-specific prompt vectors and structure-aware MoE routing to enable each expert to specialize in distinct subdomains and dynamically contribute to predictions. To promote diversity and prevent expert collapse, we introduce a soft orthogonality constraint across prompt vectors, encouraging expert specialization and facilitating a more balanced expert utilization. Additionally, we adopt a prompt-only fine-tuning strategy that significantly reduces spatiotemporal complexity during transfer. We validate GMoPE through extensive experiments under various pretraining strategies and multiple downstream tasks. Results show that GMoPE consistently outperforms state-of-the-art baselines and achieves performance comparable to full parameter fine-tuning-while requiring only a fraction of the adaptation overhead. Our work provides a principled and scalable framework for advancing generalizable and efficient graph foundation models.
format Preprint
id arxiv_https___arxiv_org_abs_2511_03251
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GMoPE:A Prompt-Expert Mixture Framework for Graph Foundation Models
Wang, Zhibin
Zhang, Zhixing
Wang, Shuqi
Xie, Xuanting
Kang, Zhao
Machine Learning
Artificial Intelligence
Social and Information Networks
Graph Neural Networks (GNNs) have demonstrated impressive performance on task-specific benchmarks, yet their ability to generalize across diverse domains and tasks remains limited. Existing approaches often struggle with negative transfer, scalability issues, and high adaptation costs. To address these challenges, we propose GMoPE (Graph Mixture of Prompt-Experts), a novel framework that seamlessly integrates the Mixture-of-Experts (MoE) architecture with prompt-based learning for graphs. GMoPE leverages expert-specific prompt vectors and structure-aware MoE routing to enable each expert to specialize in distinct subdomains and dynamically contribute to predictions. To promote diversity and prevent expert collapse, we introduce a soft orthogonality constraint across prompt vectors, encouraging expert specialization and facilitating a more balanced expert utilization. Additionally, we adopt a prompt-only fine-tuning strategy that significantly reduces spatiotemporal complexity during transfer. We validate GMoPE through extensive experiments under various pretraining strategies and multiple downstream tasks. Results show that GMoPE consistently outperforms state-of-the-art baselines and achieves performance comparable to full parameter fine-tuning-while requiring only a fraction of the adaptation overhead. Our work provides a principled and scalable framework for advancing generalizable and efficient graph foundation models.
title GMoPE:A Prompt-Expert Mixture Framework for Graph Foundation Models
topic Machine Learning
Artificial Intelligence
Social and Information Networks
url https://arxiv.org/abs/2511.03251