# DiffMove: Group Mobility Tendency Enhanced Trajectory Recovery via Diffusion Model

arXiv: https://arxiv.org/abs/2503.18302 · HTML: https://mlsanity.com/paper/2503.18302/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 22 of its 66 references that are in the map.
- First posted on arXiv 24 Mar 2025.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Imagic: Text-Based Real Image Editing with Diffusion Models](https://mlsanity.com/paper/2210.09276/) (2022)
- [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://mlsanity.com/paper/2111.14822/) (2021)
- [LINE: Large-scale Information Network Embedding](https://mlsanity.com/paper/1503.03578/) (2015)
- [CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation](https://mlsanity.com/paper/2107.03502/) (2021)
- [Deep Graph Contrastive Representation Learning](https://mlsanity.com/paper/2006.04131/) (2020)
- [Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models](https://mlsanity.com/paper/2208.09399/) (2022)
- [ControlTraj: Controllable Trajectory Generation with Topology-Constrained Diffusion Model](https://mlsanity.com/paper/2404.15380/) (2024)
- [RNTrajRec: Road Network Enhanced Trajectory Recovery with Spatial-Temporal Transformer](https://mlsanity.com/paper/2211.13234/) (2022)
- [AttnMove: History Enhanced Trajectory Recovery via Attentional Network](https://mlsanity.com/paper/2101.00646/) (2021)
- [A Universal Model for Human Mobility Prediction](https://mlsanity.com/paper/2412.15294/) (2024)
- [Noise Matters: Diffusion Model-based Urban Mobility Generation with Collaborative Noise Priors](https://mlsanity.com/paper/2412.05000/) (2024)
- [Exploring universal patterns in human home-work commuting from mobile phone data](https://mlsanity.com/paper/1311.2911/) (2013)
- [EpiMob: Interactive Visual Analytics of Citywide Human Mobility Restrictions for Epidemic Control](https://mlsanity.com/paper/2007.03180/) (2020)
- [DisenHCN: Disentangled Hypergraph Convolutional Networks for Spatiotemporal Activity Prediction](https://mlsanity.com/paper/2208.06794/) (2022)
- [One Fits All: General Mobility Trajectory Modeling via Masked Conditional Diffusion](https://mlsanity.com/paper/2501.13347/) (2025)

## Abstract (arXiv)

In the real world, trajectory data is often sparse and incomplete due to low collection frequencies or limited device coverage. Trajectory recovery aims to recover these missing trajectory points, making the trajectories denser and more complete. However, this task faces two key challenges: 1) The excessive sparsity of individual trajectories makes it difficult to effectively leverage historical information for recovery; 2) Sparse trajectories make it harder to capture complex individual mobility preferences. To address these challenges, we propose a novel method called DiffMove. Firstly, we harness crowd wisdom for trajectory recovery. Specifically, we construct a group tendency graph using the collective trajectories of all users and then integrate the group mobility trends into the location representations via graph embedding. This solves the challenge of sparse trajectories being unable to rely on individual historical trajectories for recovery. Secondly, we capture individual mobility preferences from both historical and current perspectives. Finally, we integrate group mobility tendencies and individual preferences into the spatiotemporal distribution of the trajectory to recover high-quality trajectories. Extensive experiments on two real-world datasets demonstrate that DiffMove outperforms existing state-of-the-art methods. Further analysis validates the robustness of our method.