Scalable and Provably Fair Exposure Control for Large-Scale Recommender Systems
Authors:
- Riku TogashiRTRiku Togashi
- Kenshi AbeKAKenshi Abe
- Yuta SaitoYSYuta Saito
Preprint
Abstract
Typical recommendation and ranking methods aim to optimize the satisfaction of users, but they are often oblivious to their impact on the items (e.g., products, jobs, news, video) and their providers. However, there has been a growing understanding that the latter is crucial to consider for a wide range of applications, since it determines the utility of those being recommended. Prior approaches to fairness-aware recommendation optimize a regularized objective to balance user satisfaction and item fairness based on some notion such as exposure fairness. These existing methods have been shown to be effective in controlling fairness, however, most of them are computationally inefficient, limiting their applications to only unrealistically small-scale situations. This indeed implies that the literature does not yet provide a solution to enable a flexible control of exposure in the industry-scale recommender systems where millions of users and items exist. To enable a computationally efficient exposure control even for such large-scale systems, this work develops a scalable, fast, and fair method called \emph{\textbf{ex}posure-aware \textbf{ADMM} (\textbf{exADMM})}. exADMM is based on implicit alternating least squares (iALS), a conventional scalable algorithm for collaborative filtering, but optimizes a regularized objective to achieve a flexible control of accuracy-fairness tradeoff. A particular technical challenge in developing exADMM is the fact that the fairness regularizer destroys the separability of optimization subproblems for users and items, which is an essential property to ensure the scalability of iALS. Therefore, we develop a set of optimization tools to enable yet scalable fairness control with provable convergence guarantees as a basis of our algorithm.Keywords
All Related Versions
- Version 1, 2024-02-22, ArXiv
- Published version: , 3307.
This publication has 29 references indexed in Scilit:
- Fairness for Robust Learning to Rank2023
- Multistakeholder recommendation: Survey and research directionsUser Modeling and User-Adapted Interaction, 2020
- Constrained Tensor Factorization with Accelerated AO-ADMM2017
- Exposure diversity as a design principle for recommender systemsInformation, Communication & Society, 2016
- Parallel Multi-Block ADMM with o(1 / k) ConvergenceJournal of Scientific Computing, 2016
- LorSLIM: Low Rank Sparse Linear Methods for Top-N Recommendations2014
- Fairness-aware Learning through Regularization Approach2011
- Collaborative Filtering for Implicit Feedback Datasets2008
- The long tail of recommender systems and how to leverage it2008
- Large-Scale Parallel Collaborative Filtering for the Netflix Prize2008