# REPLAY: Modeling Time-Varying Temporal Regularities of Human Mobility for Location Prediction over Sparse Trajectories

arXiv: https://arxiv.org/abs/2402.16310 · HTML: https://mlsanity.com/paper/2402.16310/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 84 references that are in the map.
- First posted on arXiv 26 Feb 2024.

## Builds on (most cited first, 11 of 11)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [A Recurrent Latent Variable Model for Sequential Data](https://mlsanity.com/paper/1506.02216/) (2015)
- [STAN: Spatio-Temporal Attention Network for Next Location Recommendation](https://mlsanity.com/paper/2102.04095/) (2021)
- [Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences](https://mlsanity.com/paper/1610.09513/) (2016)
- [GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendation](https://mlsanity.com/paper/2303.04741/) (2023)
- [Sequential Click Prediction for Sponsored Search with Recurrent Neural Networks](https://mlsanity.com/paper/1404.5772/) (2014)
- [Discovering Collaborative Signals for Next POI Recommendation with Iterative Seq2Graph Augmentation](https://mlsanity.com/paper/2106.15814/) (2021)
- [Learning to Route with Sparse Trajectory Sets---Extended Version](https://mlsanity.com/paper/1802.07980/) (2018)
- [Location Prediction via Bi-direction Speculation and Dual-level Association](https://mlsanity.com/paper/2106.15070/) (2021)
- [TribeFlow: Mining & Predicting User Trajectories](https://mlsanity.com/paper/1511.01032/) (2015)

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

- [Beyond Regularity: Modeling Chaotic Mobility Patterns for Next Location Prediction](https://mlsanity.com/paper/2509.11713/) (2025)
- [STRelay: A Universal Spatio-Temporal Relaying Framework for Location Prediction over Human Trajectory Data](https://mlsanity.com/paper/2508.16620/) (2025)
- [EviRec: Continual Evidence Learning for Dual Cold-Start POI Recommendation](https://mlsanity.com/paper/2609.20313/) (2026)

## Abstract (arXiv)

Location prediction forecasts a user's location based on historical user mobility traces. To tackle the intrinsic sparsity issue of real-world user mobility traces, spatiotemporal contexts have been shown as significantly useful. Existing solutions mostly incorporate spatiotemporal distances between locations in mobility traces, either by feeding them as additional inputs to Recurrent Neural Networks (RNNs) or by using them to search for informative past hidden states for prediction. However, such distance-based methods fail to capture the time-varying temporal regularities of human mobility, where human mobility is often more regular in the morning than in other periods, for example; this suggests the usefulness of the actual timestamps besides the temporal distances. Against this background, we propose REPLAY, a general RNN architecture learning to capture the time-varying temporal regularities for location prediction. Specifically, REPLAY not only resorts to the spatiotemporal distances in sparse trajectories to search for the informative past hidden states, but also accommodates the time-varying temporal regularities by incorporating smoothed timestamp embeddings using Gaussian weighted averaging with timestamp-specific learnable bandwidths, which can flexibly adapt to the temporal regularities of different strengths across different timestamps. Our extensive evaluation compares REPLAY against a sizable collection of state-of-the-art techniques on two real-world datasets. Results show that REPLAY consistently and significantly outperforms state-of-the-art methods by 7.7%-10.5% in the location prediction task, and the bandwidths reveal interesting patterns of the time-varying temporal regularities.