# DELTA: Variational Disentangled Learning for Privacy-Preserving Data Reprogramming

arXiv: https://arxiv.org/abs/2509.00693 · HTML: https://mlsanity.com/paper/2509.00693/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 43 references that are in the map.
- First posted on arXiv 31 Aug 2025.

## Builds on (most cited first, 20 of 20)

- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [Censoring Representations with an Adversary](https://mlsanity.com/paper/1511.05897/) (2015)
- [Feature Engineering for Predictive Modeling using Reinforcement Learning](https://mlsanity.com/paper/1709.07150/) (2017)
- [Group-wise Reinforcement Feature Generation for Optimal and Explainable Representation Space Reconstruction](https://mlsanity.com/paper/2205.14526/) (2022)
- [Self-optimizing Feature Generation via Categorical Hashing Representation and Hierarchical Reinforcement Crossing](https://mlsanity.com/paper/2309.04612/) (2023)
- [Evolutionary Large Language Model for Automated Feature Transformation](https://mlsanity.com/paper/2405.16203/) (2024)
- [Beyond Discrete Selection: Continuous Embedding Space Optimization for Generative Feature Selection](https://mlsanity.com/paper/2302.13221/) (2023)
- [Traceable Automatic Feature Transformation via Cascading Actor-Critic Agents](https://mlsanity.com/paper/2212.13402/) (2022)
- [Traceable Group-Wise Self-Optimizing Feature Transformation Learning: A Dual Optimization Perspective](https://mlsanity.com/paper/2306.16893/) (2023)
- [Reinforcement-Enhanced Autoregressive Feature Transformation: Gradient-steered Search in Continuous Space for Postfix Expressions](https://mlsanity.com/paper/2309.13618/) (2023)
- [Feature Selection as Deep Sequential Generative Learning](https://mlsanity.com/paper/2403.03838/) (2024)
- [Unsupervised Generative Feature Transformation via Graph Contrastive Pre-training and Multi-objective Fine-tuning](https://mlsanity.com/paper/2405.16879/) (2024)
- [Interactive Reinforcement Learning for Feature Selection with Decision Tree in the Loop](https://mlsanity.com/paper/2010.02506/) (2020)
- [Neuro-Symbolic Embedding for Short and Effective Feature Selection via Autoregressive Generation](https://mlsanity.com/paper/2404.17157/) (2024)
- [A Survey on Data-Centric AI: Tabular Learning from Reinforcement Learning and Generative AI Perspective](https://mlsanity.com/paper/2502.08828/) (2025)
- [DP2-VAE: Differentially Private Pre-trained Variational Autoencoders](https://mlsanity.com/paper/2208.03409/) (2022)
- [Rethinking Spatio-Temporal Anomaly Detection: A Vision for Causality-Driven Cybersecurity](https://mlsanity.com/paper/2507.08177/) (2025)
- [Advanced Conditional Variational Autoencoders (A-CVAE): Towards interpreting open-domain conversation generation via disentangling latent feature representation](https://mlsanity.com/paper/2207.12696/) (2022)
- [Distribution Shift Aware Neural Tabular Learning](https://mlsanity.com/paper/2508.19486/) (2025)
- [FITNESS: A Causal De-correlation Approach for Mitigating Bias in Machine Learning Software](https://mlsanity.com/paper/2305.14396/) (2023)

## Built on by (most cited first, 4 of 4)

- [Causally-Guided Automated Feature Engineering with Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2602.16435/) (2026)
- [Causally-Guided Diffusion for Stable Feature Selection](https://mlsanity.com/paper/2603.20930/) (2026)
- [Multimodal Group Emotion Recognition In-the-Wild Towards a Privacy-Safe Non-Individual Approach](https://mlsanity.com/paper/2606.07585/) (2026)
- [Vision: Data-Centric Anchoring for Robust and Interpretable Agentic AI](https://mlsanity.com/paper/2609.08216/) (2026)

## Abstract (arXiv)

In real-world applications, domain data often contains identifiable or sensitive attributes, is subject to strict regulations (e.g., HIPAA, GDPR), and requires explicit data feature engineering for interpretability and transparency. Existing feature engineering primarily focuses on advancing downstream task performance, often risking privacy leakage. We generalize this learning task under such new requirements as Privacy-Preserving Data Reprogramming (PPDR): given a dataset, transforming features to maximize target attribute prediction accuracy while minimizing sensitive attribute prediction accuracy. PPDR poses challenges for existing systems: 1) generating high-utility feature transformations without being overwhelmed by a large search space, and 2) disentangling and eliminating sensitive information from utility-oriented features to reduce privacy inferability. To tackle these challenges, we propose DELTA, a two-phase variational disentangled generative learning framework. Phase I uses policy-guided reinforcement learning to discover feature transformations with downstream task utility, without any regard to privacy inferability. Phase II employs a variational LSTM seq2seq encoder-decoder with a utility-privacy disentangled latent space design and adversarial-causal disentanglement regularization to suppress privacy signals during feature generation. Experiments on eight datasets show DELTA improves predictive performance by ~9.3% and reduces privacy leakage by ~35%, demonstrating robust, privacy-aware data transformation.