SynHAT: A Two-stage Coarse-to-Fine Diffusion Framework for Synthesizing Human Activity Traces

2026-04-16

AI Summary

This work addresses the challenge of generating realistic human activity trajectory (HAT) data, which is often hindered by privacy constraints and the difficulty of modeling complex spatiotemporal dynamics with long, irregular time intervals. To overcome these limitations, the authors propose SynHAT, a two-stage coarse-to-fine diffusion framework. It first captures coarse-grained spatiotemporal dependencies via Coarse-HADiff and then refines trajectories through behavior pattern extraction, Fine-HADiff, and semantic alignment. A novel latent-space spatiotemporal U-Net with dual Drift-Jitter branches is introduced to enhance generation fidelity and efficiency. Extensive experiments on real-world urban datasets from four countries demonstrate that SynHAT improves spatial and temporal metrics by 52% and 33%, respectively, and significantly outperforms existing methods in terms of fidelity, utility, privacy preservation, robustness, and scalability.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Security and Privacy: Data transparency and provenance

Abstract

Human activity traces (HATs) are critical for many applications, including human mobility modeling and point-of-interest (POI) recommendation. However, growing privacy concerns have severely limited access to authentic large-scale HAT datasets. Recent advances in generative AI provide new opportunities to synthesize realistic and privacy-preserving HATs for such applications. Yet two major challenges remain: (i) HATs are highly irregular and dynamic, with long and varying time intervals, making it difficult to capture their complex spatio-temporal dependencies and underlying distributions; and (ii) generative models are often computationally expensive, making long-term, fine-grained HAT synthesis inefficient. To address these challenges, we propose SynHAT, a computationally efficient coarse-to-fine HAT synthesis framework built on a novel spatio-temporal denoising diffusion model. In Stage 1, we develop Coarse-HADiff, which models the overall spatio-temporal dependencies of coarse-grained latent spatio-temporal traces. It incorporates a novel Latent Spatio-Temporal U-Net with dual Drift-Jitter branches to jointly model smooth spatial transitions and temporal variations during denoising. In Stage 2, we introduce a three-step pipeline consisting of Behavior Pattern Extraction, Fine-HADiff, which shares the same architecture as Coarse-HADiff, and Semantic Alignment to generate fine-grained latent spatio-temporal traces from the Stage 1 outputs. We extensively evaluate SynHAT in terms of data fidelity, utility, privacy, robustness, and scalability. Experiments on real-world HAT datasets from four cities across three countries show that SynHAT substantially outperforms state-of-the-art baselines, achieving 52% and 33% improvements on spatial and temporal metrics, respectively.

Problem

• Human Activity Traces
• Privacy-Preserving Synthesis
• Spatio-Temporal Dependencies
• Generative AI
• Trajectory Synthesis

Innovation

• coarse-to-fine diffusion
• spatio-temporal denoising diffusion
• Latent Spatio-Temporal U-Net
• human activity trace synthesis
• privacy-preserving generative AI