# Reciprocity in Machine Learning

arXiv: https://arxiv.org/abs/2202.09480 · HTML: https://mlsanity.com/paper/2202.09480/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 24 references that are in the map.
- First posted on arXiv 19 Feb 2022.

## Builds on (most cited first, 6 of 6)

- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Estimating Training Data Influence by Tracing Gradient Descent](https://mlsanity.com/paper/2002.08484/) (2020)
- [Scalable and accurate deep learning for electronic health records](https://mlsanity.com/paper/1801.07860/) (2018)
- [Deep Learning for Identifying Metastatic Breast Cancer](https://mlsanity.com/paper/1606.05718/) (2016)
- [AutoSVD++: An Efficient Hybrid Collaborative Filtering Model via Contractive Auto-encoders](https://mlsanity.com/paper/1704.00551/) (2017)

## Abstract (arXiv)

Machine learning is pervasive. It powers recommender systems such as Spotify, Instagram and YouTube, and health-care systems via models that predict sleep patterns, or the risk of disease. Individuals contribute data to these models and benefit from them. Are these contributions (outflows of influence) and benefits (inflows of influence) reciprocal? We propose measures of outflows, inflows and reciprocity building on previously proposed measures of training data influence. Our initial theoretical and empirical results indicate that under certain distributional assumptions, some classes of models are approximately reciprocal. We conclude with several open directions.