mlsanityData to 7 Oct 2026

MobTCast: Leveraging Auxiliary Trajectory Forecasting for Human Mobility Prediction

arXiv 2110.01401 ↗First posted 30 Sep 2021cs.LG cs.AIcited by 48

Not on the map. Why?

Abstract (arXiv)

Human mobility prediction is a core functionality in many location-based services and applications. However, due to the sparsity of mobility data, it is not an easy task to predict future POIs (place-of-interests) that are going to be visited. In this paper, we propose MobTCast, a Transformer-based context-aware network for mobility prediction. Specifically, we explore the influence of four types of context in the mobility prediction: temporal, semantic, social and geographical contexts. We first design a base mobility feature extractor using the Transformer architecture, which takes both the history POI sequence and the semantic information as input. It handles both the temporal and semantic contexts. Based on the base extractor and the social connections of a user, we employ a self-attention module to model the influence of the social context. Furthermore, unlike existing methods, we introduce a location prediction branch in MobTCast as an auxiliary task to model the geographical context and predict the next location. Intuitively, the geographical distance between the location of the predicted POI and the predicted location from the auxiliary branch should be as close as possible. To reflect this relation, we design a consistency loss to further improve the POI prediction performance. In our experimental results, MobTCast outperforms other state-of-the-art next POI prediction methods. Our approach illustrates the value of including different types of context in next POI prediction.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). Builds on 19 of its 49 references that are in the map. First posted on arXiv 30 Sep 2021.

Builds on

19 of 49 references.

References · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  5. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  6. 2018Video Action Transformer Networkcited by 316
  7. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 296
  8. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 228
  9. 2018Auxiliary Tasks in Multi-task Learningcited by 106
  10. 2021STAN: Spatio-Temporal Attention Network for Next Location Recommendationcited by 102
  11. 2019Transformer-based Acoustic Modeling for Hybrid Speech Recognitioncited by 86
  12. 2021Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentationcited by 77
7 more
  1. 2018Deep Auxiliary Learning for Visual Localization and Odometrycited by 59
  2. 2019AuxNet: Auxiliary tasks enhanced Semantic Segmentation for Automated Drivingcited by 19
  3. 2020TERMCast: Temporal Relation Modeling for Effective Urban Flow Forecastingcited by 10
  4. 2017walk2friends: Inferring Social Links from Mobility Profilescited by 7
  5. 2018A Scalable Framework for Trajectory Predictioncited by 7
  6. 2019LGLMF: Local Geographical based Logistic Matrix Factorization Model for POI Recommendationcited by 6
  7. 2020Relation Embedding for Personalised POI Recommendationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 7; 2023: 6; 2024: 18; 2025: 10; 2026: 6.

48 papers.

Sort:

By area:

  1. 2022PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecastingcited by 170
  2. 2023Where Would I Go Next? Large Language Models as Human Mobility Predictorscited by 92
  3. 2022Leveraging Language Foundation Models for Human Mobility Forecastingcited by 50
  4. 2022Contrastive Trajectory Similarity Learning with Dual-Feature Attentioncited by 44
  5. 2024Trajectory Data Management and Mining: A Survey from Deep Learning to the LLM Eracited by 23
  6. 2024Large Language Models are Zero-Shot Next Location Predictorscited by 22
  7. 2022Context-aware multi-head self-attentional neural network model for next location predictioncited by 20
  8. 2021Event-Aware Multimodal Mobility Nowcastingcited by 18
  9. 2024Large Language Models for Mobility Analysis in Transportation Systems: A Survey on Forecasting Taskscited by 15
  10. 2024TrajGPT: Controlled Synthetic Trajectory Generation Using a Multitask Transformer-Based Spatiotemporal Modelcited by 13
  11. 2022How do you go where? Improving next location prediction by learning travel mode information using transformerscited by 12
  12. 2024Poly2Vec: Polymorphic Fourier-Based Encoding of Geospatial Objects for GeoAI Applicationscited by 12
36 more
  1. 2023Revisiting Mobility Modeling with Graph: A Graph Transformer Model for Next Point-of-Interest Recommendationcited by 11
  2. 2024A Universal Model for Human Mobility Predictioncited by 10
  3. 2023Because Every Sensor Is Unique, so Is Every Pair: Handling Dynamicity in Traffic Forecastingcited by 9
  4. 2023Vision-based Multi-future Trajectory Prediction: A Surveycited by 8
  5. 2024Taming the Long Tail in Human Mobility Predictioncited by 8
  6. 2025Blurred Encoding for Trajectory Representation Learningcited by 8
  7. 2024ST-MoE-BERT: A Spatial-Temporal Mixture-of-Experts Framework for Long-Term Cross-City Mobility Predictioncited by 7
  8. 2022Human Mobility Prediction with Causal and Spatial-constrained Multi-task Networkcited by 5
  9. 2022Predicting Human Mobility via Self-supervised Disentanglement Learningcited by 5
  10. 2025CoBAD: Modeling Collective Behaviors for Human Mobility Anomaly Detectioncited by 5
  11. 2024Prompt Mining for Language-based Human Mobility Forecastingcited by 4
  12. 2025Beyond Regularity: Modeling Chaotic Mobility Patterns for Next Location Predictioncited by 3
  13. 2026Mobility-Embedded POIs: Learning What A Place Is and How It Is Used from Human Movementcited by 3
  14. 2023Navigating Out-of-Distribution Electricity Load Forecasting during COVID-19: Benchmarking energy load forecasting models without and with continual learningcited by 2
  15. 2024A Short Survey of Human Mobility Prediction in Epidemic Modeling from Transformers to LLMscited by 2
  16. 2024Enhancing Spatio-temporal Quantile Forecasting with Curriculum Learning: Lessons Learnedcited by 2
  17. 2024Back to Bayesics: Uncovering Human Mobility Distributions and Anomalies with an Integrated Statistical and Neural Frameworkcited by 2
  18. 2025Towards Physics-informed Diffusion for Anomaly Detection in Trajectoriescited by 2
  19. 2025OBSR: Open Benchmark for Spatial Representationscited by 2
  20. 2023Human Mobility Question Answering (Vision Paper)cited by 1
  21. 2024Forecasting Unseen Points of Interest Visits Using Context and Proximity Priorscited by 1
  22. 2024TrajLearn: Trajectory Prediction Learning using Deep Generative Modelscited by 1
  23. 2025MoveGPT: Scaling Mobility Foundation Models with Spatially-Aware Mixture of Expertscited by 1
  24. 2025Next Point-of-interest (POI) Recommendation Model Based on Multi-modal Spatio-temporal Context Feature Embeddingcited by 1
  25. 2025GTR-Mamba: Geometry-to-Tangent Routing Mamba for Hyperbolic POI Recommendationcited by 1
  26. 2024ST-DPGAN: A Privacy-preserving Framework for Spatiotemporal Data Generationcited by 0
  27. 2024Uncertainty-aware Human Mobility Modeling and Anomaly Detectioncited by 0
  28. 2024Encoding Agent Trajectories as Representations with Sequence Transformerscited by 0
  29. 2024TrajGEOS: Trajectory Graph Enhanced Orientation-based Sequential Network for Mobility Predictioncited by 0
  30. 2025A Foundational Individual Mobility Prediction Model based on Open-Source Large Language Modelscited by 0
  31. 2025POIFormer: A Transformer-Based Framework for Accurate and Scalable Point-of-Interest Attributioncited by 0
  32. 2026Multifaceted Scenario-Aware Hypergraph Learning for Next POI Recommendationcited by 0
  33. 2026Mag-Mamba: Modeling Coupled spatiotemporal Asymmetry for POI Recommendationcited by 0
  34. 2026TraXion: Rethinking Pre-training Frameworks for Mobility and Beyondcited by 0
  35. 2026Diverse Yet Consistent: Context-Guided Diffusion with Energy-Based Joint Refinement for Multi-Agent Motion Predictioncited by 0
  36. 2026ORBITER: Conflict-Aware Decision-Making for Agentic Last-Mile Deliverycited by 0