Filters








89,113 Hits in 3.9 sec

Experiments on Generalizability of User-Oriented Fairness in Recommender Systems [article]

Hossein A. Rahmani, Mohammadmehdi Naghiaei, Mahdi Dehghan, Mohammad Aliannejadi
2022 arXiv   pre-print
In this paper, we re-produce a user-oriented fairness study and provide extensive experiments to analyze the dependency of their proposed method on various fairness and recommendation aspects, including  ...  Relevant work on user-oriented fairness highlights the discriminative behavior of fairness-unaware recommendation algorithms towards a certain user group, defined based on users' activity level.  ...  improving user-oriented fairness in two-sided markets.  ... 
arXiv:2205.08289v1 fatcat:ytaw34p22zhrxcb2kchgmabga4

Explanation-Guided Fairness Testing through Genetic Algorithm [article]

Ming Fan, Wenying Wei, Wuxia Jin, Zijiang Yang, Ting Liu
2022 arXiv   pre-print
The fairness characteristic is a critical attribute of trusted AI systems. A plethora of research has proposed diverse methods for individual fairness testing.  ...  Moreover, ExpGA only requires prediction probabilities of the tested model, resulting in a better generalization capability to various models.  ...  ExpGA is also model-agnostic and can handle black-box models in diverse scenarios.  ... 
arXiv:2205.08335v1 fatcat:kwcxbsoif5ct3cq4m4i77rwee4

FAIR-enabling Services: Validating The Framework

Sara Ramezani, Patricia Herterich, Morane Gruenpeter, Rob Hooft, Tero Aalto
2021 Zenodo  
Feedback received will be incorporated into a further iteration of the report to be published later in 2021. Why a FAIR Assessment Framework for Data Services?  ...  FAIRsFAIR invited providers of data services – and all other interested stakeholders - across the full range of scientific disciplines to participate in a workshop to validate and further develop the FAIR  ...  Please add a link.The service provider communicates with its user community in a transparent manner.Longevity http://bit.ly/fsfAFservices• Is this objective/recommendation relevant for services in a FAIR  ... 
doi:10.5281/zenodo.4791584 fatcat:bjwrjnsv3bbzfe2wsuma4n7q6q

Personalization, Fairness, and Post-Userism [chapter]

Robin Burke
2021 Perspectives on Digital Humanism  
AbstractThe incorporation of fairness-aware machine learning presents a challenge for creators of personalized systems, such as recommender systems found in e-commerce, social media, and elsewhere.  ...  The theoretical framework of post-userism, which broadens the focus of design in HCI settings beyond the individual end user, provides an avenue for this integration.  ...  Here we are interested in fairness considerations across the end users themselves, and this requires a community orientation in how the recommendation task is understood.  ... 
doi:10.1007/978-3-030-86144-5_20 fatcat:maw7aydilzavhdlmr5gf42iomu

Opportunistic Multi-aspect Fairness through Personalized Re-ranking [article]

Nasim Sonboli, Farzad Eskandanian, Robin Burke, Weiwen Liu, Bamshad Mobasher
2020 arXiv   pre-print
In this paper, we present a re-ranking approach to fairness-aware recommendation that learns individual preferences across multiple fairness dimensions and uses them to enhance provider fairness in recommendation  ...  This work has primarily focused on developing recommendation approaches in which fairness metrics are jointly optimized along with recommendation accuracy.  ...  Usually when diversity is invoked as a desirable property of a recommender system, it is in the service of some user-oriented goal.  ... 
arXiv:2005.12974v1 fatcat:d4jjufffjbewhmgj4nt4n7yswy

Fairness in Recommendation: A Survey [article]

Yunqi Li, Hanxiong Chen, Shuyuan Xu, Yingqiang Ge, Juntao Tan, Shuchang Liu, Yongfeng Zhang
2022 arXiv   pre-print
fairness studies in recommendation.  ...  Recently, there has been growing attention on fairness considerations in recommender systems with more and more literature on approaches to promote fairness in recommendation.  ...  [112] consider user-oriented group fairness in commercial recommendation.  ... 
arXiv:2205.13619v4 fatcat:t7ycrw3vbjdyjbg53zphru6kbi

User-item matching for recommendation fairness: a view from item-providers [article]

Qiang Dong, Shuang-Shuang Xie, Xiaofan Yang, Yuan Yan Tang
2020 arXiv   pre-print
The main task of this paper is to significantly improve the coverage fairness (item-provider oriented objective), and simultaneously keep the recommendation accuracy in a high level (user oriented objective  ...  As we all know, users and item-providers are two main groups of participants in recommender systems.  ...  recommendation scenario over most existing fairness-oriented algorithms is that, it is parameter-free and thus avoids the cost of parameter optimization, with much better coverage fairness and almost  ... 
arXiv:2009.14474v1 fatcat:ymskbwg5abeapix2tnizzb753i

Recommender Systems as Multistakeholder Environments

Himan Abdollahpouri, Robin Burke, Bamshad Mobasher
2017 Proceedings of the 25th Conference on User Modeling, Adaptation and Personalization - UMAP '17  
However, in many recommendation domains, the user for whom recommendations are generated is not the only stakeholder in the recommendation outcome.  ...  For example, fairness and balance across stakeholders is important in some recommendation applications; achieving a goal such as promoting new sellers in a marketplace might be important in others.  ...  Fairness and balance are important examples of system-level objectives, and these social-welfare-oriented goals may at times run counter to individual preferences.  ... 
doi:10.1145/3079628.3079657 dblp:conf/um/AbdollahpouriBM17 fatcat:4fxewwxu6fcbrnauhnxh5pkysq

Basic framework on FAIRness of services - iteration 3

Hylke Koers, Patricia Herterich, Rob Hooft, Morane Gruenpeter, Tero Aalto, Sara Ramezani
2021 Zenodo  
This is an updated version of the initial basic framework on FAIRness of services as presented in detail in: Koers, Hylke, Herterich, Patricia, Hooft, Rob, Gruenpeter, Morane, & Aalto, Tero. (2020).  ...  Additional changes cover rewording of recommendations as well as deletions of duplicate recommendations.  ...  Additional changes cover rewording of recommendations as well as deletions of duplicate recommendations.  ... 
doi:10.5281/zenodo.4771936 fatcat:rpyfjish2redtbcvbmhirnknvi

Unintended Bias in Language Model-driven Conversational Recommendation [article]

Tianshu Shen, Jiaru Li, Mohamed Reda Bouadjenek, Zheda Mai, Scott Sanner
2022 arXiv   pre-print
orientation or location that should not affect recommendations manifests in significantly shifted price and category distributions of restaurant recommendations.  ...  unintended bias in future deployed CRS assistants with a potential reach of hundreds of millions of end-users.  ...  Fairness/Bias in Recommendation Systems Recommendation Systems (RS) provide users with personalized suggestions and can help alleviate information overload [8] .  ... 
arXiv:2201.06224v2 fatcat:ulcgerg33jgljcij33xtnfjoda

FAIR-Checker, a web tool to support the findability and reusability of digital life science resources

Thomas Rosnet, Vincent Lefort, Marie-Dominique Devignes, Alban Gaignard
2021 Zenodo  
In this work, we aim at empowering scientists and developers in FAIRifing their resources from the very early stages.  ...  FAIR principle are currently being adopted by many scientific communities. However, assessing how much a resource is FAIR is nowadays challenging.  ...  view on other FAIR recommendations such as the RDA maturity indicators, as well as the forthcoming EOSC FAIR metrics.  ... 
doi:10.5281/zenodo.5914307 fatcat:quoyveebsbdmnkkrr3ytbuj5w4

M2.10 Report on basic framework on FAIRness of services

Hylke Koers, Patricia Herterich, Rob Hooft, Morane Gruenpeter, Tero Aalto
2020 Zenodo  
Aimed at a target audience of data service owners, the model contains concrete recommendations to improve technical aspects of services (FAIR enablement, Quality of service, Openness & Connectivity) as  ...  We propose a first version of an assessment framework for the FAIRness of services, together with a process to refine this model including community consultation with a view to finalizing it in August  ...  The objectives and recommendations have been classified into a model that, at the top level, is divided into three more technically-oriented and three more socially-oriented aspects.  ... 
doi:10.5281/zenodo.4292598 fatcat:4ur4qnurg5givcmdsdyfq5adwq

M2.10 Report on basic framework on FAIRness of services

Hylke Koers, Patricia Herterich, Rob Hooft, Morane Gruenpeter, Tero Aalto
2020 Zenodo  
Aimed at a target audience of data service owners, the model contains concrete recommendations to improve technical aspects of services (FAIR enablement, Quality of service, Openness & Connectivity) as  ...  We propose a first version of an assessment framework for the FAIRness of services, together with a process to refine this model including community consultation with a view to finalizing it in August  ...  The objectives and recommendations have been classified into a model that, at the top level, is divided into three more technically-oriented and three more socially-oriented aspects.  ... 
doi:10.5281/zenodo.5473015 fatcat:jhygt7ms5rd3jalbvkmrza7d2q

SSCM Performance Improvement Strategy of Container Shipping Industry in Indonesia

Gena Bijaksana, Arief Daryanto, Tridoyo Kusumastanto, Nimmi Zulbainarni
2018 Indonesian Journal of Business and Entrepreneurship  
The latent variables include Technology, Integrated Logistic System, Sustainable Market Orientation and Fair-Trade System.  ...  The results show that currently the business actor and service user perceive the SSCM performance of container shipping industry in Indonesia as low.  ...  Third managerial recommendation is maintaining both Sustainable Market Orientation (SMO) and Fair-Trade System (FTS).  ... 
doi:10.17358/ijbe.4.2.179 fatcat:f3e67uya5zh3xitam2qw6guomu

D2.7 Framework for assessing FAIR Services

Sara Ramezani, Tero Aalto, Morane Gruenpeter, Patricia Herterich, Rob Hooft, Hylke Koers
2021 Zenodo  
In this work we present the FAIRsFAIR service assessment framework, a framework for assessing how well research data infrastructure services support FAIR data.  ...  This work was inspired by a combination of literature describing the expectations users have from FAIR data services, and refined by the authors based on feedback from the community gained e.g. through  ...  The recommendations in the framework are presented in seven blocks of either technical or social recommendations: Actual FAIR Enablement (how the FAIRness of the data is directly affected by the service  ... 
doi:10.5281/zenodo.5336233 fatcat:hqaqqimauzfdrcsu3vsffqqzwq
« Previous Showing results 1 — 15 out of 89,113 results