Message Tuning Outshines Graph Prompt Tuning: A Prismatic Space Perspective
For researchers in graph learning, this work provides a theoretical framework to measure adaptation capacity and a new method that surpasses existing graph prompt tuning, though it is an incremental improvement over current approaches.
The paper proposes Prismatic Space Theory (PS-Theory) to quantify the adaptation capacity of graph prompt tuning and introduces Message Tuning (MTG), which injects learnable message prototypes into GNN layers. MTG outperforms graph prompt tuning across diverse benchmarks, with empirical results supporting the theoretical claim that MTG's adaptation capacity exceeds the upper bound of graph prompt tuning.
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.