Evaluating Progress in Graph Foundation Models: A Comprehensive Benchmark and New Insights

• URL: http://arxiv.org/abs/2603.10033v1
• Date: Sat, 28 Feb 2026 04:01:10 GMT
• Title: Evaluating Progress in Graph Foundation Models: A Comprehensive Benchmark and New Insights
• Abstract summary: Graph foundation models (GFM) aim to acquire transferable knowledge by pre-training on diverse graphs.<n>Most existing GFM benchmarks vary only topic domains, obscuring how knowledge transfers across both dimensions.<n>We present a new benchmark that jointly evaluates topic and format gaps across the full GFM pipeline.
• Score: 39.21251858545552
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph foundation models (GFM) aim to acquire transferable knowledge by pre-training on diverse graphs, which can be adapted to various downstream tasks. However, domain shift in graphs is inherently two-dimensional: graphs differ not only in what they describe (topic domains) but also in how they are represented (format domains). Most existing GFM benchmarks vary only topic domains, thereby obscuring how knowledge transfers across both dimensions. We present a new benchmark that jointly evaluates topic and format gaps across the full GFM pipeline, including multi-domain self-supervised pre-training and few-shot downstream adaptation, and provides a timely evaluation of recent GFMs in the rapidly evolving landscape. Our protocol enables controlled assessment in four settings: (i) pre-training on diverse topics and formats, while adapting to unseen downstream datasets; (ii) same pre-training as in (i), while adapting to seen datasets; (iii) pre-training on a single topic domain, while adapting to other topics; (iv) pre-training on a base format, while adapting to other formats. This two-axis evaluation disentangles semantic generalization from robustness to representational shifts. We conduct extensive evaluations of eight state-of-the-art GFMs on 33 datasets spanning seven topic domains and six format domains, surfacing new empirical observations and practical insights for future research. Codes/data are available at https://github.com/smufang/GFMBenchmark.

Related papers

• GFMate: Empowering Graph Foundation Models with Test-time Prompt Tuning [41.859993506122194]
  Recent research has extended graph prompts to improve Graph Foundation Models (GFMs)<n>Most existing methods embed source-domain information into prompts, which serve either as input to GFMs or encoded during model pre-training.<n>Motivated by these insights, this paper aims to empower GFMs with pre-training-agnostic test-time graph prompt tuning, named GFMate.
  arXiv  Detail & Related papers  (2026-05-14T13:22:33Z)
• Modality-free Graph In-context Alignment [14.497854061852292]
  Modality-Free Graph In-context Alignment (MF-GIA) is a framework that makes a pretrained graph encoder promptable for few-shot prediction across heterogeneous domains.<n>MF-GIA captures domain characteristics through gradient fingerprints, which parameterize lightweight transformations.<n>Experiments demonstrate that MF-GIA achieves superior few-shot performance across diverse graph domains.
  arXiv  Detail & Related papers  (2026-03-13T07:45:34Z)
• Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement [9.87623531653534]
  Graph foundation models (GFM) offer strong domain generalization but are usually trained on single machines.<n>We propose FedGFM, a novel decentralized GFM training paradigm.<n>Key challenge is knowledge entanglement, where multi-domain knowledge merges into indistinguishable representations.<n>We present FedGFM+, an enhanced framework with two core modules to reduce knowledge entanglement.
  arXiv  Detail & Related papers  (2025-05-19T04:06:32Z)
• Revisiting, Benchmarking and Understanding Unsupervised Graph Domain Adaptation [31.106636947179005]
  Unsupervised Graph Domain Adaptation involves the transfer of knowledge from a label-rich source graph to an unlabeled target graph. We present the first comprehensive benchmark for unsupervised graph domain adaptation named GDABench. We observe that the performance of current UGDA models varies significantly across different datasets and adaptation scenarios.
  arXiv  Detail & Related papers  (2024-07-09T06:44:09Z)
• Position: Graph Foundation Models are Already Here [53.737868336014735]
  Graph Foundation Models (GFMs) are emerging as a significant research topic in the graph domain. We propose a novel perspective for the GFM development by advocating for a graph vocabulary'' This perspective can potentially advance the future GFM design in line with the neural scaling laws.
  arXiv  Detail & Related papers  (2024-02-03T17:24:36Z)
• OpenGDA: Graph Domain Adaptation Benchmark for Cross-network Learning [42.48479966907126]
  OpenGDA is a benchmark for evaluating graph domain adaptation models. It provides abundant pre-processed and unified datasets for different types of tasks. It integrates state-of-the-art models with standardized and end-to-end pipelines.
  arXiv  Detail & Related papers  (2023-07-21T04:11:43Z)
• Improving Domain Generalization with Domain Relations [77.63345406973097]
  This paper focuses on domain shifts, which occur when the model is applied to new domains that are different from the ones it was trained on. We propose a new approach called D$3$G to learn domain-specific models. Our results show that D$3$G consistently outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-02-06T08:11:16Z)
• Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation [78.28390172958643]
  We identify two key aspects that can help to alleviate multiple domain-shifts in the multi-target domain adaptation (MTDA) We propose Curriculum Graph Co-Teaching (CGCT) that uses a dual classifier head, with one of them being a graph convolutional network (GCN) which aggregates features from similar samples across the domains. When the domain labels are available, we propose Domain-aware Curriculum Learning (DCL), a sequential adaptation strategy that first adapts on the easier target domains, followed by the harder ones.
  arXiv  Detail & Related papers  (2021-04-01T23:41:41Z)
• Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning [85.6386289476598]
  We develop a novel adversarial graph representation adaptation (AGRA) framework for cross-domain holistic-local feature co-adaptation. We conduct extensive and fair evaluations on several popular benchmarks and show that the proposed AGRA framework outperforms previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-08-03T15:00:31Z)
• Supervised Domain Adaptation: A Graph Embedding Perspective and a Rectified Experimental Protocol [87.76993857713217]
  We show that Domain Adaptation methods using pair-wise relationships between source and target domain data can be formulated as a Graph Embedding. Specifically, we analyse the loss functions of three existing state-of-the-art Supervised Domain Adaptation methods and demonstrate that they perform Graph Embedding.
  arXiv  Detail & Related papers  (2020-04-23T15:46:20Z)

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.