TI-GFM: Test-Time Invariant Prototype Learning for Text-Attributed Graph Foundation Models

Graph foundation models (GFMs) aim to transfer pretrained graph encoders across domains and tasks. For text-attributed graphs, semantic class prototypes provide a direct interface for zero-shot prediction, but cross-domain shift can misalign them with target-domain class distributions. A shifted prototype may drift away from its corresponding class or approach confusing classes, leading to unreliable prototype-based prediction. Here, we introduce a Prototype Shift ($\mathcal{P}\mathcal{S}$) metric to quantify this misalignment by combining intra-class deviation and nearest inter-class separation in the target domain. Based on this diagnosis, we propose TI-GFM, a test-time invariant prototype learning framework for text-attributed GFMs. TI-GFM learns perturbation-robust representations through Text-Attributed Graph Pre-training (TGP) and refines semantic prototypes at test time using target nodes with prediction consistency across perturbed graph views. This design injects invariant target-domain evidence into semantic prototypes without retraining the backbone encoder. Experiments on seven cross-domain target datasets show that TI-GFM achieves the best average rank and the best accuracy on six of seven zero-shot node classification benchmarks, with consistent gains in few-shot node classification and zero-shot link prediction. Ablations, $\mathcal{P}\mathcal{S}$ analysis, and theoretical margin analysis further indicate that reducing prototype shift is a main factor behind cross-domain transfer performance in text-attributed GFMs.