Robustness to Missing Features using Hierarchical Clustering with Split Neural Networks (Student Abstract)
Name
SA-346.KhinchaR.pdf
Description
Submitted version
Size
251.93 KB
Format
Adobe PDF
Checksum (MD5)
959ecf6e8c1a7468bb47118f0c138353
Author(s)
Khincha, Rishab
Sarawgi, Utkarsh
Zulfikar, Wazeer
Maes, Pattie
Date Issued
May 18, 2021
Journal
THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Citation
Khincha, Rishab, Sarawgi, Utkarsh, Zulfikar, Wazeer and Maes, Pattie. 2021. "Robustness to Missing Features using Hierarchical Clustering with Split Neural Networks (Student Abstract)." THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 35 (18).
Version
Author's final manuscript
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.
Subjects
General Medicine
MIT Department
Program in Media Arts and Sciences (Massachusetts Institute of Technology)
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1609/aaai.v35i18.17905
