Search papers, labs, and topics across Lattice.
MobiDiff introduces a novel discrete diffusion framework for generating human mobility data by directly denoising multi-channel semantic skeletons, which allows for the modeling of discrete semantic events with explicit structures. This approach overcomes limitations of existing methods that rely on continuous or latent traces, providing a more efficient and interpretable solution for synthesizing realistic mobility patterns. Evaluations on large-scale datasets demonstrate that MobiDiff not only preserves essential trajectory characteristics but also achieves significant speed improvements, being 5.3 times faster than the leading method, GeoGen, during inference.
MobiDiff achieves a 5.3x speedup in generating synthetic mobility data while maintaining high fidelity to real-world patterns.
Human mobility data are essential for transportation optimization, urban planning, and resource allocation, yet real-world mobility data are costly to collect and difficult to share due to privacy concerns. Recent diffusion-based methods have shown promise in synthesizing realistic mobility patterns, but they typically rely on continuous or latent spatio-temporal traces, limiting their ability to natively model discrete semantic events with explicit region, activity, time, and interval structures. To address this issue, we introduce MobiDiff, an end-to-end discrete diffusion framework that efficiently generates mobility data by directly denoising multi-channel semantic skeletons, avoiding the costly interpolation, latent trace construction, and coarse-to-fine realization pipelines widely used in existing diffusion-based methods. Specifically, MobiDiff decomposes each human check-in event into spatial, activity, and temporal channels, and employs structured event-, group-, and channel-level masking to jointly capture trajectory-level mobility patterns and within-event dependencies. We evaluate generation fidelity, privacy-preserving, and efficiency on three large-scale real-world datasets from Atlanta, Boston, and Seattle. Results show that MobiDiff effectively preserves trajectory length and temporal interval distributions while remaining competitive across broader mobility statistics; it is also much faster than state-of-the-art methods, e.g., 5.3$\times$ faster than GeoGen on average during inference. These findings suggest that discrete diffusion offers an interpretable and efficient framework for synthetic mobility data generation.
