Search papers, labs, and topics across Lattice.
SynHAT, a two-stage coarse-to-fine diffusion framework, is introduced to synthesize realistic and privacy-preserving human activity traces (HATs) by addressing the challenges of irregular spatio-temporal dependencies and computational expense. The framework employs Coarse-HADiff in the first stage to model coarse-grained latent spatio-temporal traces using a novel Latent Spatio-Temporal U-Net with dual Drift-Jitter branches, followed by a three-step pipeline in the second stage to generate fine-grained traces. Experiments on real-world datasets demonstrate that SynHAT outperforms state-of-the-art baselines, achieving significant improvements in spatial and temporal metrics.
Generating synthetic human activity traces that are both realistic and privacy-preserving is now significantly more achievable, thanks to a novel coarse-to-fine diffusion framework that boosts spatio-temporal fidelity by over 30%.
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.
