Using Autoencoders and AutoDiff to Reconstruct Missing Variables in a Set of Time Series

TL;DR

This paper introduces a flexible method using autoencoders and automatic differentiation to reconstruct missing variables in time series data, allowing dynamic input-output configurations without retraining.

Contribution

The proposed approach enables variable reconstruction in time series using a fixed autoencoder, adaptable to different missing variable scenarios through optimization.

Findings

Effective for reconstructing one missing variable

Works reasonably well with multiple missing variables

Applicable to nonlinear electrical component data

Abstract

Existing black box modeling approaches in machine learning suffer from a fixed input and output feature combination. In this paper, a new approach to reconstruct missing variables in a set of time series is presented. An autoencoder is trained as usual with every feature on both sides and the neural network parameters are fixed after this training. Then, the searched variables are defined as missing variables at the autoencoder input and optimized via automatic differentiation. This optimization is performed with respect to the available features loss calculation. With this method, different input and output feature combinations of the trained model can be realized by defining the searched variables as missing variables and reconstructing them. The combination can be changed without training the autoencoder again. The approach is evaluated on the base of a strongly nonlinear electrical component. It is working well for one of four variables missing and generally even for multiple missing variables.