[2601.21149] Mobility-Embedded POIs: Learning What A Place Is and How It Is Used from Human Movement

Computer Science > Machine Learning arXiv:2601.21149 (cs) [Submitted on 29 Jan 2026 (v1), last revised 5 Mar 2026 (this version, v2)] Title:Mobility-Embedded POIs: Learning What A Place Is and How It Is Used from Human Movement Authors:Maria Despoina Siampou, Shushman Choudhury, Shang-Ling Hsu, Neha Arora, Cyrus Shahabi View a PDF of the paper titled Mobility-Embedded POIs: Learning What A Place Is and How It Is Used from Human Movement, by Maria Despoina Siampou and 4 other authors View PDF HTML (experimental) Abstract:Recent progress in geospatial foundation models highlights the importance of learning general-purpose representations for real-world locations, particularly points-of-interest (POIs) where human activity concentrates. Existing approaches, however, focus primarily on place identity derived from static textual metadata, or learn representations tied to trajectory context, which capture movement regularities rather than how places are actually used (i.e., POI's function). We argue that POI function is a missing but essential signal for general POI representations. We introduce Mobility-Embedded POIs (ME-POIs), a framework that augments POI embeddings derived, from language models with large-scale human mobility data to learn POI-centric, context-independent representations grounded in real-world usage. ME-POIs encodes individual visits as temporally contextualized embeddings and aligns them with learnable POI representations via contrastive learning to capture...