HI-PMK: A Data-Dependent Kernel for Incomplete Heterogeneous Data Representation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Youran, Bouadjenek, Mohamed Reda, Wells, Jonathan, Aryal, Sunil
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913963139137536
author Zhou, Youran
Bouadjenek, Mohamed Reda
Wells, Jonathan
Aryal, Sunil
author_facet Zhou, Youran
Bouadjenek, Mohamed Reda
Wells, Jonathan
Aryal, Sunil
contents Handling incomplete and heterogeneous data remains a central challenge in real-world machine learning, where missing values may follow complex mechanisms (MCAR, MAR, MNAR) and features can be of mixed types (numerical and categorical). Existing methods often rely on imputation, which may introduce bias or privacy risks, or fail to jointly address data heterogeneity and structured missingness. We propose the \textbf{H}eterogeneous \textbf{I}ncomplete \textbf{P}robability \textbf{M}ass \textbf{K}ernel (\textbf{HI-PMK}), a novel data-dependent representation learning approach that eliminates the need for imputation. HI-PMK introduces two key innovations: (1) a probability mass-based dissimilarity measure that adapts to local data distributions across heterogeneous features (numerical, ordinal, nominal), and (2) a missingness-aware uncertainty strategy (MaxU) that conservatively handles all three missingness mechanisms by assigning maximal plausible dissimilarity to unobserved entries. Our approach is privacy-preserving, scalable, and readily applicable to downstream tasks such as classification and clustering. Extensive experiments on over 15 benchmark datasets demonstrate that HI-PMK consistently outperforms traditional imputation-based pipelines and kernel methods across a wide range of missing data settings. Code is available at: https://github.com/echoid/Incomplete-Heter-Kernel
format Preprint
id arxiv_https___arxiv_org_abs_2501_04300
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HI-PMK: A Data-Dependent Kernel for Incomplete Heterogeneous Data Representation
Zhou, Youran
Bouadjenek, Mohamed Reda
Wells, Jonathan
Aryal, Sunil
Machine Learning
Handling incomplete and heterogeneous data remains a central challenge in real-world machine learning, where missing values may follow complex mechanisms (MCAR, MAR, MNAR) and features can be of mixed types (numerical and categorical). Existing methods often rely on imputation, which may introduce bias or privacy risks, or fail to jointly address data heterogeneity and structured missingness. We propose the \textbf{H}eterogeneous \textbf{I}ncomplete \textbf{P}robability \textbf{M}ass \textbf{K}ernel (\textbf{HI-PMK}), a novel data-dependent representation learning approach that eliminates the need for imputation. HI-PMK introduces two key innovations: (1) a probability mass-based dissimilarity measure that adapts to local data distributions across heterogeneous features (numerical, ordinal, nominal), and (2) a missingness-aware uncertainty strategy (MaxU) that conservatively handles all three missingness mechanisms by assigning maximal plausible dissimilarity to unobserved entries. Our approach is privacy-preserving, scalable, and readily applicable to downstream tasks such as classification and clustering. Extensive experiments on over 15 benchmark datasets demonstrate that HI-PMK consistently outperforms traditional imputation-based pipelines and kernel methods across a wide range of missing data settings. Code is available at: https://github.com/echoid/Incomplete-Heter-Kernel
title HI-PMK: A Data-Dependent Kernel for Incomplete Heterogeneous Data Representation
topic Machine Learning
url https://arxiv.org/abs/2501.04300