Recover Missing Sensor Data with Iterative Imputing Network
This addresses data quality issues in sensor-based ML tasks, but it is incremental as it builds on existing imputation methods with a novel network.
The paper tackles the problem of missing sensor data by proposing a model that captures latent temporal dynamics, significantly outperforming previous interpolation-based methods on the Beijing air quality and meteorological dataset, with consistent superiority across different missing rates.
Sensor data has been playing an important role in machine learning tasks, complementary to the human-annotated data that is usually rather costly. However, due to systematic or accidental mis-operations, sensor data comes very often with a variety of missing values, resulting in considerable difficulties in the follow-up analysis and visualization. Previous work imputes the missing values by interpolating in the observational feature space, without consulting any latent (hidden) dynamics. In contrast, our model captures the latent complex temporal dynamics by summarizing each observation's context with a novel Iterative Imputing Network, thus significantly outperforms previous work on the benchmark Beijing air quality and meteorological dataset. Our model also yields consistent superiority over other methods in cases of different missing rates.