Message Tuning Outshines Graph Prompt Tuning: A Prismatic Space Perspective

• URL: http://arxiv.org/abs/2606.03290v1
• Date: Tue, 02 Jun 2026 07:52:54 GMT
• Title: Message Tuning Outshines Graph Prompt Tuning: A Prismatic Space Perspective
• Abstract summary: Graph Foundation Models (GFMs) have emerged as a research hotspot in graph learning.<n>Recent methods explain why graph prompt tuning works, but how to rigorously measure its adaptation capacity remains an open problem.<n>We introduce Message Tuning for GFMs (MTG), a lightweight approach that injects a small set of learnable message prototypes into each layer of the GNN backbone.
• Score: 23.433958741344536
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Graph Foundation Models (GFMs), built upon the Pre-training and Adaptation paradigm, have emerged as a research hotspot in graph learning. For GNN-based GFMs, graph prompt tuning has become the prevailing adaptation method for downstream tasks. Although recent methods explain why graph prompt tuning works, how to rigorously measure its adaptation capacity remains an open problem. Addressing this problem is critical for understanding the capability limits of graph prompt tuning and for developing more powerful adaptation methods. In this paper, we propose Prismatic Space Theory (PS-Theory), a novel mathematical framework to quantify the capacity of adaptation methods, while focusing on establishing the upper bound for the adaptation capacity of graph prompt tuning. Building upon the proposed PS-Theory, we further introduce Message Tuning for GFMs (MTG), a lightweight approach that injects a small set of learnable message prototypes into each layer of the GNN backbone to adaptively guide message fusion without updating pre-trained weights. Through our PS-Theory, we prove that the adaptation capacity of MTG can exceed the theoretical upper bound of graph prompt tuning. Extensive experiments demonstrate that MTG consistently outperforms graph prompt baselines across diverse benchmark datasets, providing strong empirical support for our theoretical findings.

Related papers

• Robust Graph Fine-Tuning with Adversarial Graph Prompting [14.478430685982028]
  We propose a novel Adversarial Graph Prompting (AGP) framework to achieve robust graph fine-tuning.<n>For inner, we propose Joint Projected Gradient Descent (PGD) algorithm to generate strong adversarial noise.<n>For their outer, we employ a simple yet effective module to learn the optimal node prompts to counteract the adversarial noise.
  arXiv  Detail & Related papers  (2026-01-01T06:20:10Z)
• Learning and Editing Universal Graph Prompt Tuning via Reinforcement Learning [14.196891839610975]
  We propose a novel model and paradigm, Learning and Editing Universal GrAph Prompt Tuning (LEAP)<n>LEAP preserves the theoretical foundation of universal graph prompt tuning while pursuing more ideal prompts.<n>We show that LEAP consistently outperforms fine-tuning and other prompt-based approaches.
  arXiv  Detail & Related papers  (2025-12-09T16:12:21Z)
• GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning [92.19531718298744]
  Graph Foundation Models (GFMs) hold promise for broad applicability across diverse graph tasks and domains.<n>Existing GFMs struggle with unstable few-shot fine-tuning.<n>We propose GRAVER, a novel Generative gRAph VocabulariEs for Robust GFM fine-tuning framework.
  arXiv  Detail & Related papers  (2025-11-05T13:07:26Z)
• GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning [50.40400074353263]
  Graph Neural Networks (GNNs) are powerful tools for precessing relational data but often struggle to generalize to unseen graphs.<n>We introduce textbfGraph textbfIn-context textbfL textbfTransformer (GILT), a framework built on an LLM-free and tuning-free architecture.
  arXiv  Detail & Related papers  (2025-10-06T08:09:15Z)
• HetGPT: Harnessing the Power of Prompt Tuning in Pre-Trained Heterogeneous Graph Neural Networks [22.775933880072294]
  HetGPT is a post-training prompting framework for graph neural networks.<n>It improves the performance of state-of-the-art HGNNs on semi-supervised node classification.
  arXiv  Detail & Related papers  (2023-10-23T19:35:57Z)
• Deep Prompt Tuning for Graph Transformers [55.2480439325792]
  Fine-tuning is resource-intensive and requires storing multiple copies of large models. We propose a novel approach called deep graph prompt tuning as an alternative to fine-tuning. By freezing the pre-trained parameters and only updating the added tokens, our approach reduces the number of free parameters and eliminates the need for multiple model copies.
  arXiv  Detail & Related papers  (2023-09-18T20:12:17Z)
• Gradient Gating for Deep Multi-Rate Learning on Graphs [62.25886489571097]
  We present Gradient Gating (G$2$), a novel framework for improving the performance of Graph Neural Networks (GNNs) Our framework is based on gating the output of GNN layers with a mechanism for multi-rate flow of message passing information across nodes of the underlying graph.
  arXiv  Detail & Related papers  (2022-10-02T13:19:48Z)
• Universal Prompt Tuning for Graph Neural Networks [10.250964386142819]
  We introduce a universal prompt-based tuning method called Graph Prompt Feature (GPF) for pre-trained GNN models under any pre-training strategy. GPF operates on the input graph's feature space and can theoretically achieve an equivalent effect to any form of prompting function. Our method significantly outperforms existing specialized prompt-based tuning methods when applied to models utilizing the pre-training strategy they specialize in.
  arXiv  Detail & Related papers  (2022-09-30T05:19:27Z)
• MentorGNN: Deriving Curriculum for Pre-Training GNNs [61.97574489259085]
  We propose an end-to-end model named MentorGNN that aims to supervise the pre-training process of GNNs across graphs. We shed new light on the problem of domain adaption on relational data (i.e., graphs) by deriving a natural and interpretable upper bound on the generalization error of the pre-trained GNNs.
  arXiv  Detail & Related papers  (2022-08-21T15:12:08Z)
• Robust Optimization as Data Augmentation for Large-scale Graphs [117.2376815614148]
  We propose FLAG (Free Large-scale Adversarial Augmentation on Graphs), which iteratively augments node features with gradient-based adversarial perturbations during training. FLAG is a general-purpose approach for graph data, which universally works in node classification, link prediction, and graph classification tasks.
  arXiv  Detail & Related papers  (2020-10-19T21:51:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.