Skip to content

DAEMA: Denoising Autoencoder with Mask Attention

Missing data is a recurrent and challenging problem, especially when using machine learning algorithms for real-world applications. For this reason, missing data imputation has become an active research area, in which recent deep learning approaches have achieved state-of-the-art results. We propose DAEMA: Denoising Autoencoder with Mask Attention, an algorithm based on a denoising autoencoder architecture with an attention mechanism.
While most imputation algorithms use incomplete inputs as they would use complete data – up to basic preprocessing (e.g. mean imputation) – DAEMA leverages a mask-based attention mechanism to focus on the observed values of its inputs.
We evaluate DAEMA both in terms of reconstruction capabilities and downstream prediction and show that it achieves superior performance to state-of-the-art algorithms on several publicly available real-world datasets under various missingness settings.

The paper won the third-best paper award of ICANN 2021! It is freely accessible in its preprint form:

Simon Tihon*, Muhammad Usama Javaid*, Damien Fourure, Nicolas Posocco, Thomas Peel, DAEMA: Denoising Autoencoder with Mask Attention, In Proc. of the The 30th International Conference on Artificial Neural Networks, 2021.

* equal contributions

Watch the presentation on YouTube.

Releated Posts

We Collaborate on the TAUDoS Project

We started a new collaboration with Aix-Marseille University, Montreal University, Nantes University, and St-Etienne on a four-year project called TAUDoS, which focuses on Trustful AI.
Read More

DEBS 2022

In June 2022, our research director Sabri Skhiri and the head of the data science department at Madalina Ciortan travelled to Copenhagen to attend DEBS 2022, the leading conference focusing on distributed and event-based systems.
Read More