mlsanityData to 14 Oct 2026

View Space: Learning Representation across Arbitrary Graphs

arXiv 2512.11561 ↗First posted 12 Dec 2025cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Generalizing pretrained models to unseen datasets without retraining is a central challenge toward foundation models. Achieving fully inductive inference on numerical data is particularly difficult due to large variations in feature dimensionality and semantics across datasets. We observe that, in the presence of graph structure, numerical data admits a distinct structure-induced representational axis beyond the feature space, which we formalize as the view space. This view space enables a unified representation of graphs with heterogeneous features and motivates Graph View Transformation (GVT), a class of parametric mappings that can be shared across arbitrary graphs. We instantiate this framework with Recurrent GVT, an architecture for fully inductive node representation learning in node classification. Pretrained on OGBN-Arxiv and evaluated on 27 benchmarks, Recurrent GVT outperforms GraphAny, the prior fully inductive graph model, by +8.93%, and surpasses 12 individually tuned GNNs by at least +3.30%. These results establish the view space as a principled and practical foundation for learning across graphs with heterogeneous feature spaces. Code and checkpoints are available in https://github.com/dooho00/graph-view-space.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 61 of its 75 references that are in the map. First posted on arXiv 12 Dec 2025.

Builds on

61 of 75 references.

References · 61

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2020Language Models are Few-Shot Learnerscited by 32,419
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  6. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  7. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  8. 2017Graph Attention Networkscited by 8,923
  9. 2017Inductive Representation Learning on Large Graphscited by 6,320
  10. 2018How Powerful are Graph Neural Networks?cited by 4,393
  11. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  12. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
38 more
  1. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  2. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  3. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  4. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  5. 2019Simplifying Graph Convolutional Networkscited by 1,477
  6. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  7. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
  8. 2019Strategies for Pre-training Graph Neural Networkscited by 971
  9. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 877
  10. 2020Simple and Deep Graph Convolutional Networkscited by 860
  11. 2021How Attentive are Graph Attention Networks?cited by 835
  12. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
  13. 2019Big Transfer (BiT): General Visual Representation Learningcited by 769
  14. 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 674
  15. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 631
  16. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  17. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 595
  18. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 506
  19. 2019Provably Powerful Graph Networkscited by 389
  20. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
  21. 2021Transformers Can Do Bayesian Inferencecited by 360
  22. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 343
  23. 2023A Survey on Oversmoothing in Graph Neural Networkscited by 247
  24. 2023One for All: Towards Training One Graph Model for All Classification Taskscited by 243
  25. 2017struc2vec: Learning Node Representations from Structural Identitycited by 215
  26. 2023NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classificationcited by 210
  27. 2023SGFormer: Simplifying and Empowering Transformers for Large-Graph Representationscited by 133
  28. 2023Edge Directionality Improves Learning on Heterophilic Graphscited by 90
  29. 2024All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretrainingcited by 86
  30. 2024Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classificationcited by 85
  31. 2022Graph Attention Multi-Layer Perceptroncited by 83
  32. 2025SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptationcited by 62
  33. 2021On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphscited by 49
  34. 2021Node Dependent Local Smoothing for Scalable Graph Learningcited by 45
  35. 2024Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insightscited by 44
  36. 2023Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?cited by 41
  37. 2024Fully-inductive Node Classification on Arbitrary Graphscited by 39
  38. 2023Graph Positional and Structural Encodercited by 33

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Node4All: Learning Node Representation Beyond Datasetscited by 2
  2. 2026Neural Message Passing on Structural Interaction Graphs for Fully-Inductive Graph Neural Networkscited by 0
  3. 2026Message Passing Does More with Less for In-Context Learning on Graphscited by 0
  4. 2026NodeGround: A Node Classification Benchmark in the Graph Foundation Model Eracited by 0
  5. 2026MAGIC: Topology-Aware Analytic Graph Few-Shot Class-Incremental Learningcited by 0