litlas
ログインアカウント作成

Managing Popularity Bias in Recommender Systems with Personalized Re-Ranking

著者: Himan Abdollahpouri, Robin Burke, Bamshad Mobasher - FLAIRS 2019 被引用: 107

Many recommender systems suffer from popularity bias: popular items are recommended frequently while less popular, niche products, are recommended rarely or not at all. However, recommending the ignored products in the ``long tail'' is critical for businesses as they are less likely to be discovered. In this paper, we introduce a personalized diversification re-ranking approach to increase the representation of less popular items in recommendations while maintaining acceptable recommendation accuracy. Our approach is a post-processing step that can be applied to the output of any recommender system. We show that our approach is capable of managing popularity bias more effectively, compared with an existing method based on regularization. We also examine both new and existing metrics to measure the coverage of long-tail items in the recommendation.

The long tail ofrecommender systems and…The long tail of recommender systems and how to leverage itImproving AggregateRecommendation Diversit…Improving Aggregate Recommendation Diversity Using Ranking-Based TechniquesNovelty and diversitymetrics for recommender…Novelty and diversity metrics for recommender systems: Choice, discovery and relevanceThe MovieLens Datasets:History and ContextThe MovieLens Datasets: History and ContextTowardsMulti-Stakeholder…Towards Multi-Stakeholder Utility Evaluation of Recommender SystemsEducationalRecommendation with…Educational Recommendation with Multiple StakeholdersControlling PopularityBias in Learning-to-Ran…Controlling Popularity Bias in Learning-to-Rank RecommendationStatistical biases inInformation Retrieval…Statistical biases in Information Retrieval metrics for recommender systemsA Clustering Approachfor Personalizing…A Clustering Approach for Personalizing Diversity in Collaborative Recommender SystemsPersonalizingFairness-aware…Personalizing Fairness-aware Re-rankingIntent-aware Item-basedCollaborative Filtering…Intent-aware Item-based Collaborative Filtering for Personalised DiversificationBeyond Personalization:Research Directions in…Beyond Personalization: Research Directions in Multistakeholder RecommendationMeasuring and MitigatingItem…Measuring and Mitigating Item Under-Recommendation Bias in Personalized Ranking SystemsMultistakeholderrecommendation: Survey…Multistakeholder recommendation: Survey and research directionsGraph ConvolutionalNeural Network for a…Graph Convolutional Neural Network for a Pharmacy Cross-Selling Recommender SystemPopularity-OpportunityBias in Collaborative…Popularity-Opportunity Bias in Collaborative FilteringPopularity Bias inDynamic RecommendationPopularity Bias in Dynamic RecommendationInvestigating the impactof recommender systems…Investigating the impact of recommender systems on user-based and item-based popularity biasUser-oriented Fairnessin RecommendationUser-oriented Fairness in RecommendationUser-item matching forrecommendation fairness…User-item matching for recommendation fairness: a view from item-providersEvaluating unfairness ofpopularity bias in…Evaluating unfairness of popularity bias in recommender systems: A comprehensive user-centric analysisEqBal-RS: Mitigatingpopularity bias in…EqBal-RS: Mitigating popularity bias in recommender systemsA review on individualand multistakeholder…A review on individual and multistakeholder fairness in tourism recommender systemsEquiRate: balancedrating injection…EquiRate: balanced rating injection approach for popularity bias mitigation in recommender systemsManaging Popularity Biasin Recommender Systems…Managing Popularity Bias in Recommender Systems with Personalized Re-Ranking過去の参考文献中心の論文この論文を引用する論文古い新しい

ノードをクリックするとフォーカスを固定、空白をクリックすると本論文に戻ります。ホバーで一時的にプレビューできます。各ノードのページはタイトルから開けます。