# Learning to Limit Data Collection via Scaling Laws: A Computational Interpretation for the Legal Principle of Data Minimization

arXiv: https://arxiv.org/abs/2107.08096 · HTML: https://mlsanity.com/paper/2107.08096/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 46 references that are in the map.
- First posted on arXiv 16 Jul 2021.

## Builds on (most cited first, 12 of 12)

- [Deep Learning Scaling is Predictable, Empirically](https://mlsanity.com/paper/1712.00409/) (2017)
- [Why Is My Classifier Discriminatory?](https://mlsanity.com/paper/1805.12002/) (2018)
- [Translation-based Recommendation](https://mlsanity.com/paper/1707.02410/) (2017)
- [Towards Robust and Reproducible Active Learning Using Neural Networks](https://mlsanity.com/paper/2002.09564/) (2020)
- [Data Minimization for GDPR Compliance in Machine Learning Models](https://mlsanity.com/paper/2008.04113/) (2020)
- [Operationalizing the Legal Principle of Data Minimization for Personalization](https://mlsanity.com/paper/2005.13718/) (2020)
- [Learning to Rank Learning Curves](https://mlsanity.com/paper/2006.03361/) (2020)
- [Active Feature Acquisition with Supervised Matrix Completion](https://mlsanity.com/paper/1802.05380/) (2018)
- [Reviving Purpose Limitation and Data Minimisation in Data-Driven Systems](https://mlsanity.com/paper/2101.06203/) (2021)
- [Differential Data Analysis for Recommender Systems](https://mlsanity.com/paper/1310.0894/) (2013)
- [A Utility-Theoretic Approach to Privacy in Online Services](https://mlsanity.com/paper/1401.3859/) (2014)
- [Understanding Software Developers' Approach towards Implementing Data Minimization](https://mlsanity.com/paper/1808.01479/) (2018)

## Built on by (most cited first, 9 of 9)

- [On the Trade-Off between Actionable Explanations and the Right to be Forgotten](https://mlsanity.com/paper/2208.14137/) (2022)
- [Scaling Laws Do Not Scale](https://mlsanity.com/paper/2307.03201/) (2023)
- [The Data Minimization Principle in Machine Learning](https://mlsanity.com/paper/2405.19471/) (2024)
- [Participatory Personalization in Classification](https://mlsanity.com/paper/2302.03874/) (2023)
- [From Principle to Practice: Vertical Data Minimization for Machine Learning](https://mlsanity.com/paper/2311.10500/) (2023)
- [Engineering the Law-Machine Learning Translation Problem: Developing Legally Aligned Models](https://mlsanity.com/paper/2504.16969/) (2025)
- [SoK: Data Minimization in Machine Learning](https://mlsanity.com/paper/2508.10836/) (2025)
- [What Data is Really Necessary? A Feasibility Study of Inference Data Minimization for Recommender Systems](https://mlsanity.com/paper/2508.21547/) (2025)
- [Only Whats Necessary: Pareto Optimal Data Minimization for Privacy Preserving Video Anomaly Detection](https://mlsanity.com/paper/2603.26354/) (2026)

## Abstract (arXiv)

Modern machine learning systems are increasingly characterized by extensive personal data collection, despite the diminishing returns and increasing societal costs of such practices. Yet, data minimisation is one of the core data protection principles enshrined in the European Union's General Data Protection Regulation ('GDPR') and requires that only personal data that is adequate, relevant and limited to what is necessary is processed. However, the principle has seen limited adoption due to the lack of technical interpretation. In this work, we build on literature in machine learning and law to propose FIDO, a Framework for Inhibiting Data Overcollection. FIDO learns to limit data collection based on an interpretation of data minimization tied to system performance. Concretely, FIDO provides a data collection stopping criterion by iteratively updating an estimate of the performance curve, or the relationship between dataset size and performance, as data is acquired. FIDO estimates the performance curve via a piecewise power law technique that models distinct phases of an algorithm's performance throughout data collection separately. Empirical experiments show that the framework produces accurate performance curves and data collection stopping criteria across datasets and feature acquisition algorithms. We further demonstrate that many other families of curves systematically overestimate the return on additional data. Results and analysis from our investigation offer deeper insights into the relevant considerations when designing a data minimization framework, including the impacts of active feature acquisition on individual users and the feasability of user-specific data minimization. We conclude with practical recommendations for the implementation of data minimization.