Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models
The imputation of missing values represents a significant obstacle for many real-world data analysis pipelines. Here, we focus on time series data and put forward SSSD, an imputation model that relies on two emerging technologies, (conditional) diffusion models as state-of-the-art generative models and structured state space models as internal model architecture, which are particularly suited to capture long-term dependencies in time series data. We demonstrate that SSSD matches or even exceeds state-of-the-art probabilistic imputation and forecasting performance on a broad range of data sets and different missingness scenarios, including the challenging blackout-missing scenarios, where prior approaches failed to provide meaningful results.
Code (1)
Tasks
ImputationMissing ValuesState Space ModelsTime SeriesTime Series AnalysisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
FADTI: Fourier and Attention Driven Diffusion for Multivariate Time Series Imputation
Multivariate time series imputation is fundamental in applications such as healthcare, traffic forecasting, and biological modeling, where sensor failures and irregular sampling lead to pervasive missing values. However,…
Multivariate Time Series ImputationCSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation
The imputation of missing values in time series has many applications in healthcare and finance. While autoregressive models are natural candidates for time series imputation, score-based diffusion models have recently o…
Audio SynthesisImage GenerationImputationMissing Values+2Self-Supervised Learning of Time Series Representation via Diffusion Process and Imputation-Interpolation-Forecasting Mask
Time Series Representation Learning (TSRL) focuses on generating informative representations for various Time Series (TS) modeling tasks. Traditional Self-Supervised Learning (SSL) methods in TSRL fall into four main cat…
Anomaly DetectionImputationRepresentation LearningSelf-Supervised Learning+1Diffusion-TS: Interpretable Diffusion for General Time Series Generation
Denoising diffusion probabilistic models (DDPMs) are becoming the leading paradigm for generative models. It has recently shown breakthroughs in audio synthesis, time series imputation and forecasting. In this paper, we …
Audio SynthesisDecoderDenoisingImputation+2Self-attention-based Diffusion Model for Time-series Imputation in Partial Blackout Scenarios
Missing values in multivariate time series data can harm machine learning performance and introduce bias. These gaps arise from sensor malfunctions, blackouts, and human error and are typically addressed by data imputati…
ImputationMissing ValuesTime Series