arrow
返回

A Multi-Objective Optimization Framework for Multi-Stakeholder Fairness-Aware Recommendation

delete2022-12-21
delete25
PRE
AI
H
Haolun Wu *
C
Chen Ma *
B
Bhaskar Mitra
F
Fernando Díaz
X
Xue Liu
DOI:10.1145/3564285delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Nowadays, most online services are hosted onmulti-stakeholder marketplaces, where consumers and producers may have different objectives. Conventional recommendation systems, however, mainly focus on maximizing consumers' satisfaction by recommending the most relevant items to each individual. This may result in unfair exposure of items, thus jeopardizing producer benefits. Additionally, they do not care whether consumers from diverse demographic groups are equally satisfied. To address these limitations, we propose a multi-objective optimization framework for fairness-aware recommendation, Multi-FR, that adaptively balances accuracy and fairness for various stakeholders with Pareto optimality guarantee. We first propose four fairness constraints on consumers and producers. In order to train the whole framework in an end-to-end way, we utilize the smooth rank and stochastic ranking policy to make these fairness criteria differentiable and friendly to back-propagation. Then, we adopt themultiple gradient descent algorithm to generate a Pareto set of solutions, from which the most appropriate one is selected by the Least Misery Strategy. The experimental results demonstrate that Multi-FR largely improves recommendation fairness on multiple stakeholders over the state-of-the-art approaches while maintaining almost the same recommendation accuracy. The training efficiency study confirms our model's ability to simultaneously optimize different fairness constraints for many stakeholders efficiently.
Keyword:
Fairness-aware recommendation
multi-stakeholder
multi-objective optimization
Pareto optimal

期刊

ACM Transactions on Information Systems 封面图
ACM Transactions on Information Systems
IF:
9.1
论文数:
1.2K
被引数:
4.7K

机构

C
City University of Hong Kong
学者数:
2.3W
论文数: 3.0W
被引数: 6.1W
M
McGill University
学者数:
5.5W
论文数: 4.9W
被引数: 7.0W
G
Google Incorporated
学者数:
3.5K
论文数: 1.8K
被引数: 8
学者 查看更多机构
引用论文

引用论文

err分享
err收藏
P- and E-Selectins Recognize Sialyl 6-Sulfo Lewis X, the Recently Identified L-Selectin Ligand
err2000-11-01
err0
PREAI
errKatsuyuki Ohmori; Kayoko Kanda; Chikako Mitsuoka; Akiko Kanamori; Kazumi Kurata-Miura; Katsutoshi Sasaki; Tatsunari Nishi; Takuya Tamatani; Reiji Kannagi
err分享
err收藏
Voltage Tunability of Quantum Cascade Lasers
err2009-06-01
err0
PREAI
errYu Yao; Zhijun Liu; Anthony J. Hoffman; Kale J. Franz; Claire F. Gmachl
err分享
err收藏
Safety and tolerability of inhaled hypertonic saline in young children with cystic fibrosis
err2008-09-30
err0
PREAI
errElisabeth P. Dellon; Scott H. Donaldson; Robin Johnson; Stephanie D. Davis
err分享
err收藏
err分享
err收藏
err
IF0
err
err0
PREAI
err
err分享
err收藏
学者 查看更多内容