# INO-SGD: Addressing Utility Imbalance under Individualized Differential Privacy

arXiv: https://arxiv.org/abs/2605.07930 · HTML: https://mlsanity.com/paper/2605.07930/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 93 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 10 of 10)

- [Differentially Private Synthetic Data via Foundation Model APIs 1: Images](https://mlsanity.com/paper/2305.15560/) (2023)
- [DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?](https://mlsanity.com/paper/2106.12576/) (2021)
- [DP-SGD vs PATE: Which Has Less Disparate Impact on GANs?](https://mlsanity.com/paper/2111.13617/) (2021)
- [Revisiting Hyperparameter Tuning with Differential Privacy](https://mlsanity.com/paper/2211.01852/) (2022)
- [Clip Body and Tail Separately: High Probability Guarantees for DPSGD with Heavy Tails](https://mlsanity.com/paper/2405.17529/) (2024)
- [FairDP: Certified Fairness with Differential Privacy](https://mlsanity.com/paper/2305.16474/) (2023)
- [DP-HyPO: An Adaptive Private Hyperparameter Optimization Framework](https://mlsanity.com/paper/2306.05734/) (2023)
- [GradStop: Exploring Training Dynamics in Unsupervised Outlier Detection through Gradient](https://mlsanity.com/paper/2412.08501/) (2024)
- [Bias-Aware Minimisation: Understanding and Mitigating Estimator Bias in Private SGD](https://mlsanity.com/paper/2308.12018/) (2023)
- [Differentially Private Hyperparameter Tuning using Local Bayesian Optimization](https://mlsanity.com/paper/2502.06044/) (2025)

## Abstract (arXiv)

Differential privacy (DP) is widely employed in machine learning to protect confidential or sensitive training data from being revealed. As data owners gain greater control over their data due to personal data ownership, they are more likely to set their own privacy requirements, necessitating individualized DP (IDP) to fulfil such requests. In particular, owners of data from more sensitive subsets, such as positive cases of stigmatized diseases, likely set stronger privacy requirements, as leakage of such data could incur more serious societal impact. However, existing IDP algorithms induce a critical utility imbalance problem: Data from owners with stronger privacy requirements may be severely underrepresented in the trained model, resulting in poorer performance on similar data from subsequent users during deployment. In this paper, we analyze this problem and propose the INO-SGD algorithm, which strategically down-weights data within each batch to improve performance on the more private data across all iterations. Notably, our algorithm is specially designed to satisfy IDP, while existing techniques addressing utility imbalance neither satisfy IDP nor can be easily adapted to do so. Lastly, we demonstrate the empirical feasibility of our approach.