# Can We Predict Your Next Move Without Breaking Your Privacy?

arXiv: https://arxiv.org/abs/2507.08843 · HTML: https://mlsanity.com/paper/2507.08843/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 8 Jul 2025.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Spatio-temporal Diffusion Point Processes](https://mlsanity.com/paper/2305.12403/) (2023)
- [Efficient World Models with Context-Aware Tokenization](https://mlsanity.com/paper/2406.19320/) (2024)
- [Region Embedding with Intra and Inter-View Contrastive Learning](https://mlsanity.com/paper/2211.08975/) (2022)
- [Virtual Augmentation Supported Contrastive Learning of Sentence Representations](https://mlsanity.com/paper/2110.08552/) (2021)
- [Learning Temporal Point Processes for Efficient Retrieval of Continuous Time Event Sequences](https://mlsanity.com/paper/2202.11485/) (2022)
- [LightMove: A Lightweight Next-POI Recommendation for Taxicab Rooftop Advertising](https://mlsanity.com/paper/2108.04993/) (2021)
- [Category-Aware Location Embedding for Point-of-Interest Recommendation](https://mlsanity.com/paper/1907.13376/) (2019)

## Abstract (arXiv)

We propose FLLL3M--Federated Learning with Large Language Models for Mobility Modeling--a privacy-preserving framework for Next-Location Prediction (NxLP). By retaining user data locally and leveraging LLMs through an efficient outer product mechanism, FLLL3M ensures high accuracy with low resource demands. It achieves SOT results on Gowalla (Acc@1: 12.55, MRR: 0.1422), WeePlace (10.71, 0.1285), Brightkite (10.42, 0.1169), and FourSquare (8.71, 0.1023), while reducing parameters by up to 45.6% and memory usage by 52.7%.