To Learn is to Wander: Learning Across Graphs and Tasks with Random Walks

Excerpt

arXiv:2610.06694v2 Announce Type: replace Abstract: 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