# Incentives in Private Collaborative Machine Learning

arXiv: https://arxiv.org/abs/2404.01676 · HTML: https://mlsanity.com/paper/2404.01676/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 71 references that are in the map.
- First posted on arXiv 2 Apr 2024.

## Builds on (most cited first, 30 of 35)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [Towards Efficient Data Valuation Based on the Shapley Value](https://mlsanity.com/paper/1902.10275/) (2019)
- [Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising](https://mlsanity.com/paper/1805.06530/) (2018)
- [Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms](https://mlsanity.com/paper/1908.08619/) (2019)
- [A Principled Approach to Data Valuation for Federated Learning](https://mlsanity.com/paper/2009.06192/) (2020)
- [Data Valuation using Reinforcement Learning](https://mlsanity.com/paper/1909.11671/) (2019)
- [A Distributional Framework for Data Valuation](https://mlsanity.com/paper/2002.12334/) (2020)
- [Collaborative Machine Learning with Incentive-Aware Model Rewards](https://mlsanity.com/paper/2010.12797/) (2020)
- [Privacy for Free: Posterior Sampling and Stochastic Gradient Monte Carlo](https://mlsanity.com/paper/1502.07645/) (2015)
- [Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy](https://mlsanity.com/paper/2009.06389/) (2020)
- [Local Differential Privacy and Its Applications: A Comprehensive Survey](https://mlsanity.com/paper/2008.03686/) (2020)
- [On the Theory and Practice of Privacy-Preserving Bayesian Data Analysis](https://mlsanity.com/paper/1603.07294/) (2016)
- [Featurized Density Ratio Estimation](https://mlsanity.com/paper/2107.02212/) (2021)
- [Robust Bayesian inference via coarsening](https://mlsanity.com/paper/1506.06101/) (2015)
- [Differentially Private Bayesian Linear Regression](https://mlsanity.com/paper/1910.13153/) (2019)
- [Optimal and Differentially Private Data Acquisition: Central and Local Mechanisms](https://mlsanity.com/paper/2201.03968/) (2022)
- [Trading Data For Learning: Incentive Mechanism For On-Device Federated Learning](https://mlsanity.com/paper/2009.05604/) (2020)
- [Incentivizing Collaboration in Machine Learning via Synthetic Data Rewards](https://mlsanity.com/paper/2112.09327/) (2021)
- [Differentially Private Bayesian Inference for Exponential Families](https://mlsanity.com/paper/1809.02188/) (2018)
- [R'enyi Differential Privacy Mechanisms for Posterior Sampling](https://mlsanity.com/paper/1710.00892/) (2017)
- [Differentially Private Bayesian Inference for Generalized Linear Models](https://mlsanity.com/paper/2011.00467/) (2020)
- [Truthful Data Acquisition via Peer Prediction](https://mlsanity.com/paper/2006.03992/) (2020)
- [Not one but many Tradeoffs: Privacy Vs. Utility in Differentially Private Machine Learning](https://mlsanity.com/paper/2008.08807/) (2020)
- [PASS-GLM: polynomial approximate sufficient statistics for scalable Bayesian GLM inference](https://mlsanity.com/paper/1709.09216/) (2017)
- [How to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning](https://mlsanity.com/paper/2007.09370/) (2020)
- [Incentives for Federated Learning: a Hypothesis Elicitation Approach](https://mlsanity.com/paper/2007.10596/) (2020)
- [Minimax Optimal Estimation of KL Divergence for Continuous Distributions](https://mlsanity.com/paper/2002.11599/) (2020)

## Built on by (most cited first, 10 of 10)

- [Learning Reconfigurable Representations for Multimodal Federated Learning with Missing Data](https://mlsanity.com/paper/2510.22880/) (2025)
- [2D-OOB: Attributing Data Contribution Through Joint Valuation Framework](https://mlsanity.com/paper/2408.03572/) (2024)
- [Promise and Peril of Collaborative Code Generation Models: Balancing Effectiveness and Memorization](https://mlsanity.com/paper/2409.12020/) (2024)
- [Federated Prompt-Tuning with Heterogeneous and Incomplete Multimodal Client Data](https://mlsanity.com/paper/2602.07081/) (2026)
- [Federated Recommender System with Data Valuation for E-commerce Platform](https://mlsanity.com/paper/2509.11196/) (2025)
- [Data value estimation on private gradients](https://mlsanity.com/paper/2412.17008/) (2024)
- [Data Sharing with a Generative AI Competitor](https://mlsanity.com/paper/2505.12386/) (2025)
- [Benchmarking Robust Aggregation in Decentralized Gradient Marketplaces](https://mlsanity.com/paper/2509.05833/) (2025)
- [Incentivizing Time-Aware Fairness in Data Sharing](https://mlsanity.com/paper/2510.09240/) (2025)
- [Incentivizing Truthfulness and Collaborative Fairness in Bayesian Learning](https://mlsanity.com/paper/2605.11889/) (2026)

## Abstract (arXiv)

Collaborative machine learning involves training models on data from multiple parties but must incentivize their participation. Existing data valuation methods fairly value and reward each party based on shared data or model parameters but neglect the privacy risks involved. To address this, we introduce differential privacy (DP) as an incentive. Each party can select its required DP guarantee and perturb its sufficient statistic (SS) accordingly. The mediator values the perturbed SS by the Bayesian surprise it elicits about the model parameters. As our valuation function enforces a privacy-valuation trade-off, parties are deterred from selecting excessive DP guarantees that reduce the utility of the grand coalition's model. Finally, the mediator rewards each party with different posterior samples of the model parameters. Such rewards still satisfy existing incentives like fairness but additionally preserve DP and a high similarity to the grand coalition's posterior. We empirically demonstrate the effectiveness and practicality of our approach on synthetic and real-world datasets.