Robustness to Missing Features using Hierarchical Clustering with Split Neural Networks (Student Abstract)

Authors

  • Rishab Khincha Massachusetts Institute of Technology BITS Pilani Goa Campus
  • Utkarsh Sarawgi Massachusetts Institute of Technology
  • Wazeer Zulfikar Massachusetts Institute of Technology
  • Pattie Maes Massachusetts Institute of Technology

DOI:

https://doi.org/10.1609/aaai.v35i18.17905

Keywords:

Missing Features, Hierarchical Clustering, Neural Networks

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.

Downloads

Published

2021-05-18

How to Cite

Khincha, R., Sarawgi, U., Zulfikar, W., & Maes, P. (2021). Robustness to Missing Features using Hierarchical Clustering with Split Neural Networks (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 15817-15818. https://doi.org/10.1609/aaai.v35i18.17905

Issue

Section

AAAI Student Abstract and Poster Program