Metraipolis › archive › dc_57832006ffe4
To Learn is to Wander: Learning Across Graphs and Tasks with Random Walks — arXiv:2610.06694
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.06694
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:31:46.260Z
- SHA-256 of the archived text
38268b6f02f746bceb9d4cdf0485f16610223f06e63437b637aff5314d6aaadc- Stable URL of this page
https://metraipolis.com/documento/dc_57832006ffe4
How to cite
To Learn is to Wander: Learning Across Graphs and Tasks with Random Walks — arXiv:2610.06694 — arXiv, https://arxiv.org/abs/2610.06694 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_57832006ffe4 (Metraipolis archive dc_57832006ffe4, sha256 38268b6f02f746bceb9d4cdf0485f16610223f06e63437b637aff5314d6aaadc)
BibTeX
@misc{dc57832006ffe4,
title = {To Learn is to Wander: Learning Across Graphs and Tasks with Random Walks — arXiv:2610.06694},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.06694},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_57832006ffe4; sha256 38268b6f02f746bceb9d4cdf0485f16610223f06e63437b637aff5314d6aaadc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06694. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Graph foundation models aim to transfer across graphs, feature spaces, relational schemas, and prediction tasks, yet existing approaches typically generalize only within particular graph modalities or tasks. We propose Wander, a graph foundation model designed to operate across these settings within a single pretrained checkpoint. Following the prior-predictive perspective, we formulate graph learning as completion of a partially observed graph. We realize this task-general view through a common interface based on random walks, allowing the same model to operate across homogeneous and multi-relational graphs with varying features, labels, and relational schemas. Wander can increase its structural context at inference time without changing its learned parameters and, under suitable assumptions, universally approximates the corresponding Bayes-optimal predictor on bounded connected graphs. Empirically, a single pretrained checkpoint achieves state-of-the-art or highly competitive results across node classification, homogeneous link prediction, and knowledge-graph link prediction. Moreover, joint pretraining across graph modalities and tasks preserves performance in specialized settings while enabling positive transfer and the composition of separately learned capabilities at inference time. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.06694 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T05:27:05.908Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).