Longitudinal Flow Matching for Trajectory Modeling
By: Mohammad Mohaiminul Islam , Thijs P. Kuipers , Sharvaree Vadgama and more
Potential Business Impact:
Helps predict future paths from scattered data.
Generative models for sequential data often struggle with sparsely sampled and high-dimensional trajectories, typically reducing the learning of dynamics to pairwise transitions. We propose Interpolative Multi-Marginal Flow Matching (IMMFM), a framework that learns continuous stochastic dynamics jointly consistent with multiple observed time points. IMMFM employs a piecewise-quadratic interpolation path as a smooth target for flow matching and jointly optimizes drift and a data-driven diffusion coefficient, supported by a theoretical condition for stable learning. This design captures intrinsic stochasticity, handles irregular sparse sampling, and yields subject-specific trajectories. Experiments on synthetic benchmarks and real-world longitudinal neuroimaging datasets show that IMMFM outperforms existing methods in both forecasting accuracy and further downstream tasks.
Similar Papers
Longitudinal Flow Matching for Trajectory Modeling
Machine Learning (CS)
Predicts future body changes from brain scans.
Multi-Marginal Stochastic Flow Matching for High-Dimensional Snapshot Data at Irregular Time Points
Machine Learning (CS)
Tracks complex changes from few, uneven snapshots.
CFMI: Flow Matching for Missing Data Imputation
Machine Learning (CS)
Fills in missing data accurately and fast.