2018/12/31 by Bashir Rastegarpanah, Krishna P. Gummadi, Mark Crovella
Computer Science · Decision Sciences · Mathematics · #Advanced Bandit Algorithms Research #Antidote #Computer science #Machine learning #Recommender Systems and Techniques #Recommender system #Risk analysis (engineering) #Set (abstract data type) #Stochastic Gradient Optimization Techniques #cs.IR #cs.LG #stat.ML
paper · pdf · doi:10.1145/3289600.3291002
References to appendices are fixed
arxiv created 2019/01/25 · arxiv updated 2019/01/29 · openalex publication_date 2019/01/30 · openalex created_date 2022/07/30 · openalex updated_date 2026/08/06
The increasing role of recommender systems in many aspects of society makes it essential to consider how such systems may impact social good. Various modifications to recommendation algorithms have been proposed to improve their performance for specific socially relevant measures. However, previous proposals are often not easily adapted to different measures, and they generally require the ability to modify either existing system inputs, the system's algorithm, or the system's outputs. As an alternative, in this paper we introduce the idea of improving the social desirability of recommender system outputs by adding more data to the input, an approach we view as as providing 'antidote' data to the system. We formalize the antidote data problem, and develop optimization-based solutions. We take as our model system the matrix factorization approach to recommendation, and we propose a set of measures to capture the polarization or fairness of recommendations. We then show how to generate antidote data for each measure, pointing out a number of computational efficiencies, and discuss the impact on overall system accuracy. Our experiments show that a modest budget for antidote data can lead to significant improvements in the polarization or fairness of recommendations.