Inflow, Outflow, and Reciprocity in Machine Learning

Mukund Sundararajan, Walid Krichene
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33195-33208, 2023.

Abstract

Data is pooled across entities (individuals or enterprises) to create machine learning models, and sometimes, the entities that contribute the data also benefit from the models. Consider for instance a recommender system (e.g. Spotify, Instagram or YouTube), a health care app that predicts the risk for some disease, or a service built by pooling data across enterprises. In this work we propose a framework to study this value exchange, i.e., we model and measure contributions (outflows), benefits (inflows) and the balance between contributions and benefits (the degree of reciprocity). We show theoretically, and via experiments that under certain distributional assumptions, some classes of models are approximately reciprocal. These results only scratch the surface; we conclude with several open directions.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-sundararajan23a, title = {Inflow, Outflow, and Reciprocity in Machine Learning}, author = {Sundararajan, Mukund and Krichene, Walid}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {33195--33208}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/sundararajan23a/sundararajan23a.pdf}, url = {https://proceedings.mlr.press/v202/sundararajan23a.html}, abstract = {Data is pooled across entities (individuals or enterprises) to create machine learning models, and sometimes, the entities that contribute the data also benefit from the models. Consider for instance a recommender system (e.g. Spotify, Instagram or YouTube), a health care app that predicts the risk for some disease, or a service built by pooling data across enterprises. In this work we propose a framework to study this value exchange, i.e., we model and measure contributions (outflows), benefits (inflows) and the balance between contributions and benefits (the degree of reciprocity). We show theoretically, and via experiments that under certain distributional assumptions, some classes of models are approximately reciprocal. These results only scratch the surface; we conclude with several open directions.} }
Endnote
%0 Conference Paper %T Inflow, Outflow, and Reciprocity in Machine Learning %A Mukund Sundararajan %A Walid Krichene %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-sundararajan23a %I PMLR %P 33195--33208 %U https://proceedings.mlr.press/v202/sundararajan23a.html %V 202 %X Data is pooled across entities (individuals or enterprises) to create machine learning models, and sometimes, the entities that contribute the data also benefit from the models. Consider for instance a recommender system (e.g. Spotify, Instagram or YouTube), a health care app that predicts the risk for some disease, or a service built by pooling data across enterprises. In this work we propose a framework to study this value exchange, i.e., we model and measure contributions (outflows), benefits (inflows) and the balance between contributions and benefits (the degree of reciprocity). We show theoretically, and via experiments that under certain distributional assumptions, some classes of models are approximately reciprocal. These results only scratch the surface; we conclude with several open directions.
APA
Sundararajan, M. & Krichene, W.. (2023). Inflow, Outflow, and Reciprocity in Machine Learning. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:33195-33208 Available from https://proceedings.mlr.press/v202/sundararajan23a.html.

Related Material