<scp>FAIR</scp>: Fairness‐aware information retrieval evaluation

Gao, Ruoyuan; Ge, Yingqiang; Shah, Chirag

doi:10.1002/asi.24648

Cited by 12 publications

(10 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Biega et al [33] introduced some measures and methods to deal with position bias in ranking which leads to unfairness and less attention to low-ranking items. Ruoyuan et al [34] considered the problem of measuring the user utility in ranking algorithms and introduced an integrated metric for evaluating fairness-aware ranking results.…”

Section: Related Workmentioning

confidence: 99%

“…CG does not consider the position of items in the recommendation list. DCG fills this gap by considering the position of each item along with its score, and is defined [34] as in Eq. ( 23):…”

Section: Evaluation Metricsmentioning

confidence: 99%

“…So, there is a need for a metric that has proper bounds so that we can take a mean across all the recommendations scores to report a final value. NDCG [34] achieves this normalization using the DCG of the ideal order (iDCG), and calculated as in Eq. ( 24):…”

Section: Evaluation Metricsmentioning

confidence: 99%

See 2 more Smart Citations

FairAC: Long-term Balancing between Accuracy and Fairness in Recommender Systems Using a Multi-Objective Deep Reinforcement Learning Framework

Gazik,

Roayaei

2024

Preprint

View full text Add to dashboard Cite

Recommender systems suggest the users with the most appropriate and accurate recommendations by reviewing and exploring user-related information (user's preferences and interests) from the user's previous experiences. Although recommender systems have been studied by many researchers in recent years, a few of them have considered the problem of balancing fairness and accuracy in dynamic recommender systems, where the interests of users change, and new items are added over time to the list of existing items. To resolve this problem, we propose a multi-objective deep reinforcement learning framework based on the actor-critic method, called \textit{FairAC}, which considers fairness in recommender systems in a dynamic environment. We conducted extensive experiments on real-world datasets. The results show that the proposed approach provides accurate and fair recommendations and surpassing the performance of prior studies by approximately 10\% in terms of both accuracy and fairness.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Evaluation Metricsmentioning

confidence: 99%

See 1 more Smart Citation

FairAC: Long-term Balancing between Accuracy and Fairness in Recommender Systems Using a Multi-Objective Deep Reinforcement Learning Framework

Gazik,

Roayaei

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…To address concerns about algorithmic fairness and bias in personalized recommendation systems, recent research has focused on developing fairness-aware models and evaluation metrics (Gao et al, 2022;Lalor et al, 2024;Zhang et al, 2023). These studies aim to mitigate bias and ensure equitable treatment across diverse user groups, promoting diversity and inclusivity in personalized recommendations.…”

Section: Personalized Information Access and User Profile Modeling: R...mentioning

confidence: 99%

Learning-Based Models for Building User Profiles for Personalized Information Access

Sassi Hidri

2024

IJIKM

View full text Add to dashboard Cite

Aim/Purpose: This study aims to evaluate the success of deep learning in building user profiles for personalized information access. Background: To better express document content and information during the matching phase of the information retrieval (IR) process, deep learning architectures could potentially offer a feasible and optimal alternative to user profile building for personalized information access. Methodology: This study uses deep learning-based models to deduce the domain of the document deemed implicitly relevant by a user that corresponds to their center of interest, and then used predicted domain by the best given architecture with user’s characteristics to predict other centers of interest. Contribution: This study contributes to the literature by considering the difference in vocabulary used to express document content and information needs. Users are integrated into all research phases in order to provide them with relevant information adapted to their context and their preferences meeting their precise needs. To better express document content and information during this phase, deep learning models are employed to learn complex representations of documents and queries. These models can capture hierarchical, sequential, or attention-based patterns in textual data. Findings: The results show that deep learning models were highly effective for building user profiles for personalized information access since they leveraged the power of neural networks in analyzing and understanding complex patterns in user behavior, preferences, and user interactions. Recommendations for Practitioners: Building effective user profiles for personalized information access is an ongoing process that requires a combination of technology, user engagement, and a commitment to privacy and security. Recommendation for Researchers: Researchers involved in building user profiles for personalized information access play a crucial role in advancing the field and developing more innovative deep-based networks solutions by exploring novel data sources, such as biometric data, sentiment analysis, or physiological signals, to enhance user profiles. They can investigate the integration of multimodal data for a more comprehensive understanding of user preferences. Impact on Society: The proposed models can provide companies with an alternative and sophisticated recommendation system to foster progress in building user profiles by analyzing complex user behavior, preferences, and interactions, leading to more effective and dynamic content suggestions. Future Research: The development of user profile evolution models and their integration into a personalized information search system may be confronted with other problems such as the interpretability and transparency of the learning-based models. Developing interpretable machine learning techniques and visualization tools to explain how user profiles are constructed and used for personalized information access seems necessary to us as a future extension of our work.

show abstract

“…In addition, these works do not consider fairness constraints. Fair Federated Learning for Recommendation: Fair ML methods for RSs have been extensively explored in centralized settings compared to federated settings (Wang et al 2023;Li, Ge, and Zhang 2021;Gao, Ge, and Shah 2022). The availability of the whole dataset makes the application of existing fairness notions straightforward in centralized learning, whereas it is challenging to apply fairness in FL.…”

Section: Related Workmentioning

confidence: 99%

No Prejudice! Fair Federated Graph Neural Networks for Personalized Recommendation

Agrawal,

Sirohi,

Kumar

et al. 2024

AAAI

View full text Add to dashboard Cite

Ensuring fairness in Recommendation Systems (RSs) across demographic groups is critical due to the increased integration of RSs in applications such as personalized healthcare, finance, and e-commerce. Graph-based RSs play a crucial role in capturing intricate higher-order interactions among entities. However, integrating these graph models into the Federated Learning (FL) paradigm with fairness constraints poses formidable challenges as this requires access to the entire interaction graph and sensitive user information (such as gender, age, etc.) at the central server. This paper addresses the pervasive issue of inherent bias within RSs for different demographic groups without compromising the privacy of sensitive user attributes in FL environment with the graph-based model. To address the group bias, we propose F2PGNN (Fair Federated Personalized Graph Neural Network), a novel framework that leverages the power of Personalized Graph Neural Network (GNN) coupled with fairness considerations. Additionally, we use differential privacy techniques to fortify privacy protection. Experimental evaluation on three publicly available datasets showcases the efficacy of F2PGNN in mitigating group unfairness by 47% ∼ 99% compared to the state-of-the-art while preserving privacy and maintaining the utility. The results validate the significance of our framework in achieving equitable and personalized recommendations using GNN within the FL landscape. Source code is at: https://github.com/nimeshagrawal/F2PGNN-AAAI24

show abstract

FAIR: Fairness‐aware information retrieval evaluation

Cited by 12 publications

References 38 publications

FairAC: Long-term Balancing between Accuracy and Fairness in Recommender Systems Using a Multi-Objective Deep Reinforcement Learning Framework

FairAC: Long-term Balancing between Accuracy and Fairness in Recommender Systems Using a Multi-Objective Deep Reinforcement Learning Framework

Learning-Based Models for Building User Profiles for Personalized Information Access

No Prejudice! Fair Federated Graph Neural Networks for Personalized Recommendation

Contact Info

Product

Resources

About