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

Rishab Khincha, Utkarsh Sarawgi, Wazeer Zulfikar, Pattie Maes

AAAI 2021 pp. 15817-15818

doi:10.1609/AAAI.V35I18.17905 /aaai/2021/khincha2021aaai-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.

PDF AAAI Semantic Scholar

Cite

Text

Khincha et al. "Robustness to Missing Features Using Hierarchical Clustering with Split Neural Networks (Student Abstract)." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I18.17905

Markdown

[Khincha et al. "Robustness to Missing Features Using Hierarchical Clustering with Split Neural Networks (Student Abstract)." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/khincha2021aaai-robustness/) doi:10.1609/AAAI.V35I18.17905

BibTeX

@inproceedings{khincha2021aaai-robustness,
  title     = {{Robustness to Missing Features Using Hierarchical Clustering with Split Neural Networks (Student Abstract)}},
  author    = {Khincha, Rishab and Sarawgi, Utkarsh and Zulfikar, Wazeer and Maes, Pattie},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {15817-15818},
  doi       = {10.1609/AAAI.V35I18.17905},
  url       = {https://mlanthology.org/aaai/2021/khincha2021aaai-robustness/}
}