Robustness to Missing Features using Hierarchical Clustering with Split Neural Networks

TL;DR

This paper introduces a novel method combining hierarchical feature clustering with split neural networks to improve robustness against missing data, outperforming traditional imputation techniques on benchmark datasets.

Contribution

It proposes a new approach that clusters features hierarchically and trains split neural networks, enhancing robustness to missing features in data analysis.

Findings

Improved performance on benchmark datasets with missing data.

Effective even with simple imputation techniques.

Learning through feature clusters enhances model robustness.

Abstract

The problem of missing data has been persistent for a long time and poses a major obstacle in machine learning and statistical data analysis. Past works in this field have tried using various data imputation techniques to fill in the missing data, or training neural networks (NNs) with the missing data. In this work, we propose a simple yet effective approach that clusters similar input features together using hierarchical clustering and then trains proportionately split neural networks with a joint loss. We evaluate this approach on a series of benchmark datasets and show promising improvements even with simple imputation techniques. We attribute this to learning through clusters of similar features in our model architecture. The source code is available at https://github.com/usarawgi911/Robustness-to-Missing-Features