mlsanityData to 14 Oct 2026

Learning Graph Foundation Models on Riemannian Graph-of-Graphs

arXiv 2605.09993 ↗First posted 11 May 2026cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Graph foundation models (GFMs), pretrained on massive graph data, have transformed graph machine learning by supporting general-purpose reasoning across diverse graph tasks and domains. Existing GFMs pretrained with fixed-hop subgraph sampling impose a fixed receptive field, causing scale mismatch on diverse tasks, which often require heterogeneous and unknown structural contexts beyond a fixed sampling scale. We propose R-GFM, a Riemannian Graph-of-Graphs (GoG) based foundation model, that treats structural scale as a first-class citizen in modeling. R-GFM constructs a multi-scale GoG over-sampled subgraphs at different hop distances and learns geometry-adaptive representations from Riemannian manifolds. Theoretical analysis shows that R-GFM reduces structural domain generalization error compared to fixed-scale GFMs. Experiments on various datasets demonstrate that R-GFM achieves state-of-the-art performance, with up to a 49% relative improvement on downstream tasks. Our code is available at https://github.com/USTC-DataDarknessLab/R-GFM.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 52 of its 68 references that are in the map. First posted on arXiv 11 May 2026.

Builds on

52 of 68 references.

References · 52

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  6. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  7. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  8. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  9. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  10. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,139
  11. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,138
  12. 2018Deep Graph Infomaxcited by 1,106
38 more
  1. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
  2. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  3. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
  4. 2018Link Prediction Based on Graph Neural Networkscited by 832
  5. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
  6. 2015Image-based Recommendations on Styles and Substitutescited by 706
  7. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 631
  8. 2013Domain Generalization via Invariant Feature Representationcited by 623
  9. 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 593
  10. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 448
  11. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 443
  12. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 362
  13. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 343
  14. 2019Bridging Theory and Algorithm for Domain Adaptationcited by 332
  15. 2023One for All: Towards Training One Graph Model for All Classification Taskscited by 243
  16. 2023GraphGPT: Graph Instruction Tuning for Large Language Modelscited by 226
  17. 2022Vision GNN: An Image is Worth Graph of Nodescited by 186
  18. 2023GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networkscited by 167
  19. 2022Not too little, not too much: a theoretical analysis of graph (over)smoothingcited by 106
  20. 2022Universal Prompt Tuning for Graph Neural Networkscited by 100
  21. 2024All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretrainingcited by 86
  22. 2024Harder Tasks Need More Experts: Dynamic Routing in MoE Modelscited by 72
  23. 2024Can GNN be Good Adapter for LLMs?cited by 71
  24. 2025SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptationcited by 62
  25. 2024GOFA: A Generative One-For-All Model for Joint Graph Language Modelingcited by 57
  26. 2024AnyGraph: Graph Foundation Model in the Wildcited by 53
  27. 2025Graph Foundation Models: A Comprehensive Surveycited by 44
  28. 2025Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignmentcited by 42
  29. 2023Generalized Graph Prompt: Toward a Unification of Pre-Training and Downstream Tasks on Graphscited by 39
  30. 2023Simple and Asymmetric Graph Contrastive Learning without Augmentationscited by 38
  31. 2025RiemannGFM: Learning a Graph Foundation Model from Riemannian Geometrycited by 35
  32. 2024Non-Homophilic Graph Pre-Training and Prompt Learningcited by 31
  33. 2020GoGNN: Graph of Graphs Neural Network for Predicting Structured Entity Interactionscited by 29
  34. 2023Provably Powerful Graph Neural Networks for Directed Multigraphscited by 27
  35. 2024GraphMoRE: Mitigating Topological Heterogeneity via Mixture of Riemannian Expertscited by 24
  36. 2025Beyond Message Passing: Neural Graph Pattern Machinecited by 17
  37. 2024Noise-Resilient Unsupervised Graph Representation Learning via Multi-Hop Feature Quality Estimationcited by 11
  38. 2025Generative Graph Pattern Machinecited by 11

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026AgentGFM: A Graph Foundation Model with Node-Agent Information-Flow Controlcited by 0
  2. 2026OpenMAS-GCom. A Diagnostic Benchmark for Graph-enhanced Multi-Agent Systemscited by 0
  3. 2026MAGIC: Mixed-Granularity Agent Graphs via Incremental Construction with Dense-Reward Reinforcement Learningcited by 0