NRTSI: Non-Recurrent Time Series Imputation
This work is significant for researchers and practitioners working with time series data, especially when dealing with irregular sampling or sparse observations, by providing a more robust imputation method.
This paper addresses the problem of missing data in time series, particularly for irregularly-sampled and sparsely observed data. The authors propose NRTSI, a non-recurrent model that reformulates time series as permutation-equivariant sets, achieving state-of-the-art performance across various imputation benchmarks.
Time series imputation is a fundamental task for understanding time series with missing data. Existing methods either do not directly handle irregularly-sampled data or degrade severely with sparsely observed data. In this work, we reformulate time series as permutation-equivariant sets and propose a novel imputation model NRTSI that does not impose any recurrent structures. Taking advantage of the permutation equivariant formulation, we design a principled and efficient hierarchical imputation procedure. In addition, NRTSI can directly handle irregularly-sampled time series, perform multiple-mode stochastic imputation, and handle data with partially observed dimensions. Empirically, we show that NRTSI achieves state-of-the-art performance across a wide range of time series imputation benchmarks.