Get Started
Home
Topics
Search
Library
Research questionHow can multivariate time-series imputers recover structured gaps under high missingness?Periodic and nonstationary dependencies can be obscured when failures remove contiguous or otherwise structured portions of multiple series. Imputation must reconstruct values while representing uncertainty when little temporal evidence remains.
AI
Diffusion Models
Evaluation & Benchmarks
Machine Learning
Research Paper
Statistical Machine Learning
Technology
Latest papersRecent research connected to this question, newest first.FADTI: Fourier and Attention Driven Diffusion for Multivariate Time Series ImputationThe source studies a Fourier- and attention-driven diffusion framework with DFT, STFT, and FSST variants, evaluated on multiple benchmarks including a biological imputation benchmark. Reported evidence covers accuracy, uncertainty estimation, and sampling efficiency, with improvements especially under high missing rates and structured missing patterns.research paper · Sep 3, 2026
Related questions
How can multimodal time-series forecasting align sparse text with heterogeneous temporal dynamics?How can synthetic medical time-series generation preserve rare-class patterns across temporal scales for downstream prediction?In multivariate forecasting, how can augmentation vary samples without breaking input–future temporal coherence?How can synthetic time-series generation preserve temporal and frequency structure when training data are scarce?