CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation

TL;DR

CSDI introduces a novel conditional score-based diffusion model for probabilistic time series imputation, outperforming existing methods in healthcare and environmental datasets by leveraging observed data correlations.

Contribution

The paper presents CSDI, a new diffusion-based imputation method explicitly trained for time series, exploiting observed data correlations for improved accuracy.

Findings

CSDI improves imputation accuracy by 40-65% over existing methods.

Deterministic CSDI reduces error by 5-20% compared to state-of-the-art methods.

CSDI is also effective for interpolation and probabilistic forecasting.

Abstract

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 outperformed existing counterparts including autoregressive models in many tasks such as image generation and audio synthesis, and would be promising for time series imputation. In this paper, we propose Conditional Score-based Diffusion models for Imputation (CSDI), a novel time series imputation method that utilizes score-based diffusion models conditioned on observed data. Unlike existing score-based approaches, the conditional diffusion model is explicitly trained for imputation and can exploit correlations between observed values. On healthcare and environmental data, CSDI improves by 40-65% over existing probabilistic imputation methods on popular performance metrics. In addition, deterministic imputation by CSDI reduces the error by 5-20% compared to the state-of-the-art deterministic imputation methods. Furthermore, CSDI can also be applied to time series interpolation and probabilistic forecasting, and is competitive with existing baselines. The code is available at https://github.com/ermongroup/CSDI.