Can graph foundation models generalize over architecture?

Conference item : Poster

Graph foundation models (GFMs) have recently attracted interest due to the promise of graph neural network (GNN) architectures that generalize zero-shot across graphs of arbitrary scales, feature dimensions, and domains. While existing work has demonstrated this ability empirically across diverse real-world benchmarks, these tasks share a crucial hidden limitation: they admit a narrow set of effective GNN architectures. In particular, current domain-agnostic GFMs rely on fixed architectural backbones, implicitly assuming that a single message-passing regime suffices across tasks. In this paper, we argue that architecture adaptivity is a necessary requirement for true GFMs. We show that existing approaches are non-robust to task-dependent architectural attributes and, as a case study, use range as a minimal and measurable axis along which this limitation becomes explicit. With theoretical analysis and controlled synthetic experiments, we demonstrate that fixed-backbone GFMs provably under-reach on tasks whose architectural requirements differ from those seen at training time. To address this issue, we introduce a framework that adapts effective GNN architecture at inference time by discovering and mixing task-specific linear graph operators, enabling zero-shot generalization across tasks with heterogeneous architectural requirements, without retraining. We validate our approach on arbitrary-range synthetic tasks and a suite of real-world benchmarks, demonstrating improved performance and robustness over existing domain-agnostic GFMs.

Authors: Gutteridge, B; Bronstein, M; Dong, X

• Publication status: Published
• Peer review status: Peer reviewed
• Article number: 118
• Publication date: 2026-03-02
• Acceptance date: 2026-03-02
• Event title: ICLR 2026 Workshop on Geometry-grounded Representation Learning and Generative Modeling
• Event location: Rio de Janeiro, Brazil
• Event website: https://gram-workshop.github.io/
• Event start date: 2026-04-26
• Event end date: 2026-04-26
• Language: English
• Keywords: long-range interactions; graph neural network; graph foundation model; range
• Subtype: Poster