Performative Recommendation: Diversifying Content via Strategic Incentives

Itay Eilat, Nir Rosenfeld
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9082-9103, 2023.

Abstract

The primary goal in recommendation is to suggest relevant content to users, but optimizing for accuracy often results in recommendations that lack diversity. To remedy this, conventional approaches such as re-ranking improve diversity by presenting more diverse items. Here we argue that to promote inherent and prolonged diversity, the system must encourage its creation. Towards this, we harness the performative nature of recommendation, and show how learning can incentivize strategic content creators to create diverse content. Our approach relies on a novel form of regularization that anticipates strategic changes to content, and penalizes for content homogeneity. We provide analytic and empirical results that demonstrate when and how diversity can be incentivized, and experimentally demonstrate the utility of our approach on synthetic and semi-synthetic data.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-eilat23a, title = {Performative Recommendation: Diversifying Content via Strategic Incentives}, author = {Eilat, Itay and Rosenfeld, Nir}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {9082--9103}, 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/eilat23a/eilat23a.pdf}, url = {https://proceedings.mlr.press/v202/eilat23a.html}, abstract = {The primary goal in recommendation is to suggest relevant content to users, but optimizing for accuracy often results in recommendations that lack diversity. To remedy this, conventional approaches such as re-ranking improve diversity by presenting more diverse items. Here we argue that to promote inherent and prolonged diversity, the system must encourage its creation. Towards this, we harness the performative nature of recommendation, and show how learning can incentivize strategic content creators to create diverse content. Our approach relies on a novel form of regularization that anticipates strategic changes to content, and penalizes for content homogeneity. We provide analytic and empirical results that demonstrate when and how diversity can be incentivized, and experimentally demonstrate the utility of our approach on synthetic and semi-synthetic data.} }
Endnote
%0 Conference Paper %T Performative Recommendation: Diversifying Content via Strategic Incentives %A Itay Eilat %A Nir Rosenfeld %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-eilat23a %I PMLR %P 9082--9103 %U https://proceedings.mlr.press/v202/eilat23a.html %V 202 %X The primary goal in recommendation is to suggest relevant content to users, but optimizing for accuracy often results in recommendations that lack diversity. To remedy this, conventional approaches such as re-ranking improve diversity by presenting more diverse items. Here we argue that to promote inherent and prolonged diversity, the system must encourage its creation. Towards this, we harness the performative nature of recommendation, and show how learning can incentivize strategic content creators to create diverse content. Our approach relies on a novel form of regularization that anticipates strategic changes to content, and penalizes for content homogeneity. We provide analytic and empirical results that demonstrate when and how diversity can be incentivized, and experimentally demonstrate the utility of our approach on synthetic and semi-synthetic data.
APA
Eilat, I. & Rosenfeld, N.. (2023). Performative Recommendation: Diversifying Content via Strategic Incentives. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:9082-9103 Available from https://proceedings.mlr.press/v202/eilat23a.html.

Related Material