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

arXiv: https://arxiv.org/abs/2601.21149 · HTML: https://mlsanity.com/paper/2601.21149/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 40 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Large Dual Encoders Are Generalizable Retrievers](https://mlsanity.com/paper/2112.07899/) (2021)
- [Time2Vec: Learning a Vector Representation of Time](https://mlsanity.com/paper/1907.05321/) (2019)
- [STAN: Spatio-Temporal Attention Network for Next Location Recommendation](https://mlsanity.com/paper/2102.04095/) (2021)
- [Multi-Scale Representation Learning for Spatial Feature Distributions using Grid Cells](https://mlsanity.com/paper/2003.00824/) (2020)
- [Spatial-Temporal Large Language Model for Traffic Prediction](https://mlsanity.com/paper/2401.10134/) (2024)
- [GeoLLM: Extracting Geospatial Knowledge from Large Language Models](https://mlsanity.com/paper/2310.06213/) (2023)
- [Geographic Location Encoding with Spherical Harmonics and Sinusoidal Representation Networks](https://mlsanity.com/paper/2310.06743/) (2023)
- [GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendation](https://mlsanity.com/paper/2303.04741/) (2023)
- [MobTCast: Leveraging Auxiliary Trajectory Forecasting for Human Mobility Prediction](https://mlsanity.com/paper/2110.01401/) (2021)
- [GeoLM: Empowering Language Models for Geospatially Grounded Language Understanding](https://mlsanity.com/paper/2310.14478/) (2023)
- [GATGPT: A Pre-trained Large Language Model with Graph Attention Network for Spatiotemporal Imputation](https://mlsanity.com/paper/2311.14332/) (2023)
- [SpaBERT: A Pretrained Language Model from Geographic Data for Geo-Entity Representation](https://mlsanity.com/paper/2210.12213/) (2022)
- [Positional Encoder Graph Neural Networks for Geographic Data](https://mlsanity.com/paper/2111.10144/) (2021)
- [Poly2Vec: Polymorphic Fourier-Based Encoding of Geospatial Objects for GeoAI Applications](https://mlsanity.com/paper/2408.14806/) (2024)
- [TrajGPT: Controlled Synthetic Trajectory Generation Using a Multitask Transformer-Based Spatiotemporal Model](https://mlsanity.com/paper/2411.04381/) (2024)
- [GeoReasoner: Reasoning On Geospatially Grounded Context For Natural Language Understanding](https://mlsanity.com/paper/2408.11366/) (2024)
- [POI-Enhancer: An LLM-based Semantic Enhancement Framework for POI Representation Learning](https://mlsanity.com/paper/2502.10038/) (2025)
- [Taming the Long Tail in Human Mobility Prediction](https://mlsanity.com/paper/2410.14970/) (2024)
- [Geo2Vec: Shape- and Distance-Aware Neural Representation of Geospatial Entities](https://mlsanity.com/paper/2508.19305/) (2025)

## Built on by (most cited first, 3 of 3)

- [TraXion: Rethinking Pre-training Frameworks for Mobility and Beyond](https://mlsanity.com/paper/2605.06906/) (2026)
- [TrajGANR: Trajectory-Centric Urban Multimodal Learning via Geospatially Aligned Neural Representations](https://mlsanity.com/paper/2605.06990/) (2026)
- [Plan-to-Synthesis: Cross-City Human Mobility Generation via Semantic Latent Flow Matching](https://mlsanity.com/paper/2609.32732/) (2026)

## Abstract (arXiv)

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 usage patterns across users and time. To address long-tail sparsity, we propose a novel mechanism that propagates temporal visit patterns from nearby, frequently visited POIs across multiple spatial scales. We evaluate ME-POIs on five newly proposed map enrichment tasks, testing its ability to capture both the identity and function of POIs. Across all tasks, augmenting text-based embeddings with ME-POIs consistently outperforms both text-only and mobility-only baselines. Notably, ME-POIs trained on mobility data alone can surpass text-only models on certain tasks, highlighting that POI function is a critical component of accurate and generalizable POI representations.