Learning from Anonymized and Incomplete Tabular Data
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915767329488896 |
|---|---|
| author | Lange, Lucas Böttinger, Adrian Christen, Victor Vidanage, Anushka Christen, Peter Rahm, Erhard |
| author_facet | Lange, Lucas Böttinger, Adrian Christen, Victor Vidanage, Anushka Christen, Peter Rahm, Erhard |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_01217 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning from Anonymized and Incomplete Tabular Data Lange, Lucas Böttinger, Adrian Christen, Victor Vidanage, Anushka Christen, Peter Rahm, Erhard Machine Learning Artificial Intelligence Cryptography and Security Databases 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. |
| title | Learning from Anonymized and Incomplete Tabular Data |
| topic | Machine Learning Artificial Intelligence Cryptography and Security Databases |
| url | https://arxiv.org/abs/2602.01217 |