EndtoEnd Time Series Imputation via Residual Short Paths
[edit]
Proceedings of The 10th Asian Conference on Machine Learning, PMLR 95:248263, 2018.
Abstract
Time series imputation (replacing
missing data) plays an important role in time series analysis due to missing values in real world data. How to recover missing values and model the underlying dynamic dependencies from incomplete time series remains a challenge. A recent work has found that residual networks help build very deep networks by leveraging short paths due to skip connections (Veit et al., 2016). Inspired by this, we observe that these short paths can model underlying correlations between missing items and their previous nonmissing observations in a graphlike way. Hence, we propose an endtoend imputation network with residual short paths, called Residual IMPutation LSTM (RIMPLSTM), a flexible combination of residual short paths with graphbased temporal dependencies. We construct a residual sum unit (RSU), which enables RIMPLSTM to make full use of previous revealed information to model incomplete time series and reduce the negative impact of missing values. Moreover, a switch unit is designed to detect the missing values and a new loss function is then developed to train our model with time series in the presence of missing values in an endtoend way, which also allows simultaneous imputation and prediction. Extensive empirical comparisons with other competitive imputation approaches over several synthetic and real world time series with various rates of missing data verify the superiority of our model.
Related Material


