Model-Based Approaches for Independence-Enhanced Recommendation. Kamishima, T., Akaho, S., Asoh, H., & Sato, I. In 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW), pages 860–867. doi abstract bibtex This paper studies a new approach to enhance recommendation independence. Such approaches are useful in ensuring adherence to laws and regulations, fair treatment of content providers, and exclusion of unwanted information. For example, recommendations that match an employer with a job applicant should not be based on socially sensitive information, such as gender or race, from the perspective of social fairness. An algorithm that could exclude the influence of such sensitive information would be useful in this case. We previously gave a formal definition of recommendation independence and proposed a method adopting a regularizer that imposes such an independence constraint. As no other options than this regularization approach have been put forward, we here propose a new model-based approach, which is based on a generative model that satisfies the constraint of recommendation independence. We apply this approach to a latent class model and empirically show that the model-based approach can enhance recommendation independence. Recommendation algorithms based on generative models, such as topic models, are important, because they have a flexible functionality that enables them to incorporate a wide variety of information types. Our new model-based approach will broaden the applications of independence-enhanced recommendation by integrating the functionality of generative models.
@inproceedings{kamishima_model-based_2016,
title = {Model-Based Approaches for Independence-Enhanced Recommendation},
doi = {10.1109/ICDMW.2016.0127},
abstract = {This paper studies a new approach to enhance recommendation independence. Such approaches are useful in ensuring adherence to laws and regulations, fair treatment of content providers, and exclusion of unwanted information. For example, recommendations that match an employer with a job applicant should not be based on socially sensitive information, such as gender or race, from the perspective of social fairness. An algorithm that could exclude the influence of such sensitive information would be useful in this case. We previously gave a formal definition of recommendation independence and proposed a method adopting a regularizer that imposes such an independence constraint. As no other options than this regularization approach have been put forward, we here propose a new model-based approach, which is based on a generative model that satisfies the constraint of recommendation independence. We apply this approach to a latent class model and empirically show that the model-based approach can enhance recommendation independence. Recommendation algorithms based on generative models, such as topic models, are important, because they have a flexible functionality that enables them to incorporate a wide variety of information types. Our new model-based approach will broaden the applications of independence-enhanced recommendation by integrating the functionality of generative models.},
eventtitle = {2016 {IEEE} 16th International Conference on Data Mining Workshops ({ICDMW})},
pages = {860--867},
booktitle = {2016 {IEEE} 16th International Conference on Data Mining Workshops ({ICDMW})},
author = {Kamishima, T. and Akaho, S. and Asoh, H. and Sato, I.},
date = {2016-12},
keywords = {recommender systems, Predictive models, Recommender systems, data mining, Data mining, Data models, Training, recommender system, topic model, content providers, fairness-aware data mining, independence constraint, independence-enhanced recommendation, Linear programming, model-based approaches, Random variables, recommendation algorithms, sensitive information, social fairness, topic models, unwanted information exclusion}
}
Downloads: 0
{"_id":"L2BMh8wZ96pc4Tjin","bibbaseid":"kamishima-akaho-asoh-sato-modelbasedapproachesforindependenceenhancedrecommendation","authorIDs":[],"author_short":["Kamishima, T.","Akaho, S.","Asoh, H.","Sato, I."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Model-Based Approaches for Independence-Enhanced Recommendation","doi":"10.1109/ICDMW.2016.0127","abstract":"This paper studies a new approach to enhance recommendation independence. Such approaches are useful in ensuring adherence to laws and regulations, fair treatment of content providers, and exclusion of unwanted information. For example, recommendations that match an employer with a job applicant should not be based on socially sensitive information, such as gender or race, from the perspective of social fairness. An algorithm that could exclude the influence of such sensitive information would be useful in this case. We previously gave a formal definition of recommendation independence and proposed a method adopting a regularizer that imposes such an independence constraint. As no other options than this regularization approach have been put forward, we here propose a new model-based approach, which is based on a generative model that satisfies the constraint of recommendation independence. We apply this approach to a latent class model and empirically show that the model-based approach can enhance recommendation independence. Recommendation algorithms based on generative models, such as topic models, are important, because they have a flexible functionality that enables them to incorporate a wide variety of information types. Our new model-based approach will broaden the applications of independence-enhanced recommendation by integrating the functionality of generative models.","eventtitle":"2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW)","pages":"860–867","booktitle":"2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW)","author":[{"propositions":[],"lastnames":["Kamishima"],"firstnames":["T."],"suffixes":[]},{"propositions":[],"lastnames":["Akaho"],"firstnames":["S."],"suffixes":[]},{"propositions":[],"lastnames":["Asoh"],"firstnames":["H."],"suffixes":[]},{"propositions":[],"lastnames":["Sato"],"firstnames":["I."],"suffixes":[]}],"date":"2016-12","keywords":"recommender systems, Predictive models, Recommender systems, data mining, Data mining, Data models, Training, recommender system, topic model, content providers, fairness-aware data mining, independence constraint, independence-enhanced recommendation, Linear programming, model-based approaches, Random variables, recommendation algorithms, sensitive information, social fairness, topic models, unwanted information exclusion","bibtex":"@inproceedings{kamishima_model-based_2016,\n\ttitle = {Model-Based Approaches for Independence-Enhanced Recommendation},\n\tdoi = {10.1109/ICDMW.2016.0127},\n\tabstract = {This paper studies a new approach to enhance recommendation independence. Such approaches are useful in ensuring adherence to laws and regulations, fair treatment of content providers, and exclusion of unwanted information. For example, recommendations that match an employer with a job applicant should not be based on socially sensitive information, such as gender or race, from the perspective of social fairness. An algorithm that could exclude the influence of such sensitive information would be useful in this case. We previously gave a formal definition of recommendation independence and proposed a method adopting a regularizer that imposes such an independence constraint. As no other options than this regularization approach have been put forward, we here propose a new model-based approach, which is based on a generative model that satisfies the constraint of recommendation independence. We apply this approach to a latent class model and empirically show that the model-based approach can enhance recommendation independence. Recommendation algorithms based on generative models, such as topic models, are important, because they have a flexible functionality that enables them to incorporate a wide variety of information types. Our new model-based approach will broaden the applications of independence-enhanced recommendation by integrating the functionality of generative models.},\n\teventtitle = {2016 {IEEE} 16th International Conference on Data Mining Workshops ({ICDMW})},\n\tpages = {860--867},\n\tbooktitle = {2016 {IEEE} 16th International Conference on Data Mining Workshops ({ICDMW})},\n\tauthor = {Kamishima, T. and Akaho, S. and Asoh, H. and Sato, I.},\n\tdate = {2016-12},\n\tkeywords = {recommender systems, Predictive models, Recommender systems, data mining, Data mining, Data models, Training, recommender system, topic model, content providers, fairness-aware data mining, independence constraint, independence-enhanced recommendation, Linear programming, model-based approaches, Random variables, recommendation algorithms, sensitive information, social fairness, topic models, unwanted information exclusion}\n}\n\n","author_short":["Kamishima, T.","Akaho, S.","Asoh, H.","Sato, I."],"key":"kamishima_model-based_2016","id":"kamishima_model-based_2016","bibbaseid":"kamishima-akaho-asoh-sato-modelbasedapproachesforindependenceenhancedrecommendation","role":"author","urls":{},"keyword":["recommender systems","Predictive models","Recommender systems","data mining","Data mining","Data models","Training","recommender system","topic model","content providers","fairness-aware data mining","independence constraint","independence-enhanced recommendation","Linear programming","model-based approaches","Random variables","recommendation algorithms","sensitive information","social fairness","topic models","unwanted information exclusion"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://fair-ia.ekstrandom.net/fair-ia.bib","creationDate":"2020-04-09T18:53:45.517Z","downloads":0,"keywords":["recommender systems","predictive models","recommender systems","data mining","data mining","data models","training","recommender system","topic model","content providers","fairness-aware data mining","independence constraint","independence-enhanced recommendation","linear programming","model-based approaches","random variables","recommendation algorithms","sensitive information","social fairness","topic models","unwanted information exclusion"],"search_terms":["model","based","approaches","independence","enhanced","recommendation","kamishima","akaho","asoh","sato"],"title":"Model-Based Approaches for Independence-Enhanced Recommendation","year":null,"dataSources":["FRCCaPECNMucjb6Hk"]}