NARA: Anchor-Conditioned Representation Learning for Heterogeneous Vector Geoentities

The paper introduces NARA, a self‑supervised framework for learning representations of heterogeneous vector geospatial entities such as roads, buildings, and points of interest. NARA uses spatial‑context‑aware attention to model spatial autocorrelation, masked semantic modeling, geometry‑aware relation modeling, and relation‑conditioned regularization to capture diverse spatial relations. The resulting frozen, task‑agnostic encoder outperforms specialized state‑of‑the‑art methods on traffic‑speed prediction, building‑function classification, and next point‑of‑interest prediction.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• benchmarks