Bridging Input Feature Spaces Towards Graph Foundation Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915983957950464 |
|---|---|
| author | Eliasof, Moshe Mantri, Krishna Sri Ipsit Bevilacqua, Beatrice Ribeiro, Bruno Schönlieb, Carola-Bibiane |
| author_facet | Eliasof, Moshe Mantri, Krishna Sri Ipsit Bevilacqua, Beatrice Ribeiro, Bruno Schönlieb, Carola-Bibiane |
| contents | Unlike vision and language domains, graph learning lacks a shared input space, as input features differ across graph datasets not only in semantics, but also in value ranges and dimensionality. This misalignment prevents graph models from generalizing across datasets, limiting their use as foundation models. In this work, we propose ALL-IN, a simple and theoretically grounded method that enables transferability across datasets with different input features. Our approach projects node features into a shared random space and constructs representations via covariance-based statistics, thus eliminating dependence on the original feature space. We show that the computed node-covariance operators and the resulting node representations are invariant in distribution to permutations of the input features. We further demonstrate that the expected operator exhibits invariance to general orthogonal transformations of the input features. Empirically, ALL-IN achieves strong performance across diverse node- and graph-level tasks on unseen datasets with new input features, without requiring architecture changes or retraining. These results point to a promising direction for input-agnostic, transferable graph models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_04834 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Bridging Input Feature Spaces Towards Graph Foundation Models Eliasof, Moshe Mantri, Krishna Sri Ipsit Bevilacqua, Beatrice Ribeiro, Bruno Schönlieb, Carola-Bibiane Machine Learning Unlike vision and language domains, graph learning lacks a shared input space, as input features differ across graph datasets not only in semantics, but also in value ranges and dimensionality. This misalignment prevents graph models from generalizing across datasets, limiting their use as foundation models. In this work, we propose ALL-IN, a simple and theoretically grounded method that enables transferability across datasets with different input features. Our approach projects node features into a shared random space and constructs representations via covariance-based statistics, thus eliminating dependence on the original feature space. We show that the computed node-covariance operators and the resulting node representations are invariant in distribution to permutations of the input features. We further demonstrate that the expected operator exhibits invariance to general orthogonal transformations of the input features. Empirically, ALL-IN achieves strong performance across diverse node- and graph-level tasks on unseen datasets with new input features, without requiring architecture changes or retraining. These results point to a promising direction for input-agnostic, transferable graph models. |
| title | Bridging Input Feature Spaces Towards Graph Foundation Models |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2605.04834 |