Learning from Anonymized and Incomplete Tabular Data

TL;DR

This paper introduces new data transformation methods for learning from anonymized and incomplete tabular data, demonstrating improved utility over standard approaches across various privacy scenarios.

Contribution

It proposes novel data transformation strategies tailored for heterogeneous anonymized data, addressing challenges in machine learning with privacy-preserving tabular datasets.

Findings

Generalized values outperform suppression in utility retention

Data preparation strategy effectiveness varies by scenario

Consistent data representations are key for downstream utility

Abstract

User-driven privacy allows individuals to control whether and at what granularity their data is shared, leading to datasets that mix original, generalized, and missing values within the same records and attributes. While such representations are intuitive for privacy, they pose challenges for machine learning, which typically treats non-original values as new categories or as missing, thereby discarding generalization semantics. For learning from such tabular data, we propose novel data transformation strategies that account for heterogeneous anonymization and evaluate them alongside standard imputation and LLM-based approaches. We employ multiple datasets, privacy configurations, and deployment scenarios, demonstrating that our method reliably regains utility. Our results show that generalized values are preferable to pure suppression, that the best data preparation strategy depends on the scenario, and that consistent data representations are crucial for maintaining downstream utility. Overall, our findings highlight that effective learning is tied to the appropriate handling of anonymized values.