[2603.26456] Fair Data Pre-Processing with Imperfect Attribute Space

Computer Science > Databases arXiv:2603.26456 (cs) [Submitted on 27 Mar 2026] Title:Fair Data Pre-Processing with Imperfect Attribute Space Authors:Ying Zheng, Yangfan Jiang, Kian-Lee Tan View a PDF of the paper titled Fair Data Pre-Processing with Imperfect Attribute Space, by Ying Zheng and 2 other authors View PDF HTML (experimental) Abstract:Fair data pre-processing is a widely used strategy for mitigating bias in machine learning. A promising line of research focuses on calibrating datasets to satisfy a designed fairness policy so that sensitive attributes influence outcomes only through clearly specified legitimate causal pathways. While effective on clean and information-rich data, these methods often break down in real-world scenarios with imperfect attribute spaces, where decision-relevant factors may be deemed unusable or even missing. To address this gap, we propose LatentPre, a novel framework that enables principled and robust fair data processing in practical settings. Instead of relying solely on observed attributes, LatentPre augments the fairness policy with latent attributes that capture essential but subtle signals, enabling the framework to operate as if the attribute space were perfect. These latent attributes are strategically introduced to guarantee identifiability and are estimated using a tailored expectation-maximization paradigm. The raw data is then carefully refined to conform to this latent-augmented policy, effectively removing biased pattern...