DAEMA: Denoising Autoencoder with Mask Attention

TL;DR

DAEMA introduces a novel denoising autoencoder with mask attention that effectively imputes missing data by focusing on observed values, outperforming existing methods in real-world datasets.

Contribution

The paper presents DAEMA, a new deep learning model that uses mask attention within a denoising autoencoder for improved missing data imputation.

Findings

DAEMA outperforms state-of-the-art imputation algorithms on multiple datasets.

It achieves superior reconstruction accuracy across various missingness scenarios.

DAEMA enhances downstream prediction tasks with better imputation quality.

Abstract

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.