Masked Diffusion for Travel Diaries Synthesis
New in Diffusion models; no direction yet. Diffusion models
Abstract (arXiv)
Because household travel surveys combine household characteristics, variable-length person rosters, vehicle rosters, and trip chains, existing synthesis pipelines split them across separate models or flatten them into cropped fixed-length vectors. Representation, rather than modeling, becomes the bottleneck: splitting severs cross-segment dependence, and cropping truncates the household-structure distribution. We instead tokenize the diary and keep the object whole: each household-day becomes one token sequence with count tokens for vehicles, persons, and trips, and distinct symbols for padded, hidden, unobserved, and inapplicable positions. We introduce DiaryBridge, a masked diffusion model that bridges the fully hidden sequence to the distribution of complete diaries by unmasking positions in any order. One trained model, conditioned on any observed subset, performs synthesis and partial-diary completion alike. Experiments on real data extracted from the 2017/2018 Regional Travel Survey of the Baltimore region show that DiaryBridge generates travel reflecting vehicle availability and employment status, recovers shared trips using other household members' observed diaries, and better reproduces aggregate demand across modes, purposes, and departure periods than the learned baselines.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 34 references that are in the map. First posted on arXiv 12 Oct 2026.
Builds on
17 of 34 references.
References · 17
- 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
- 2022Diffusion-LM Improves Controllable Text Generationcited by 1,027
- 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distributioncited by 745
- 2019Modeling Tabular data using Conditional GANcited by 699
- 2024Simplified and Generalized Masked Diffusion for Discrete Datacited by 626
- 2022A Continuous Time Framework for Discrete Denoising Modelscited by 451
- 2022Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioningcited by 373
- 2022Continuous diffusion for categorical datacited by 214
- 2022Latent Diffusion for Language Generationcited by 115
- 2019Prediction of rare feature combinations in population synthesis: Application of deep generative modellingcited by 19
- 2022A Deep Generative Model for Feasible and Diverse Population Synthesiscited by 17
- 2020Composite Travel Generative Adversarial Networks for Tabular and Sequential Population Synthesiscited by 12
5 more
- 2023Copula-based transferable models for synthetic population generationcited by 10
- 2025A Large Language Model for Feasible and Diverse Population Synthesiscited by 9
- 2025Synthesising Activity Participations and Scheduling with Deep Generative Machine Learningcited by 3
- 2025Generating Feasible and Diverse Synthetic Populations Using Diffusion Modelscited by 2
- 2026Sticky Jump Diffusions: A Unifying View of Masked, Continuous, and Hybrid Diffusioncited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Be More Real: Travel Diary Generation Using LLM Agents and Individual Profiles
- 2026MobiDiff: Semantic-Aware Multi-Channel Discrete Diffusion for Human Mobility Data Generation
- 2025Deep Generative Model for Human Mobility Behavior
- 2025Leveraging the Spatial Hierarchy: Coarse-to-fine Trajectory Generation via Cascaded Hybrid Diffusion
- 2024Human Mobility Modeling with Household Coordination Activities under Limited Information via Retrieval-Augmented LLMs
- 2026Coarse-to-Fine Multi-Resolution Diffusion Models for Trajectory Generation in Urban Systems
- 2024Noise Matters: Diffusion Model-based Urban Mobility Generation with Collaborative Noise Priors
- 2025Dynamic Population Distribution Aware Human Trajectory Generation with Diffusion Model