Fairness-aware News Recommendation with Decomposed Adversarial Learning

  title={Fairness-aware News Recommendation with Decomposed Adversarial Learning},
  author={Chuhan Wu and Fangzhao Wu and Xiting Wang and Yongfeng Huang and Xing Xie},
News recommendation is important for online news services. Existing news recommendation models are usually learned from users' news click behaviors. Usually the behaviors of users with the same sensitive attributes (e.g., genders) have similar patterns and news recommendation models can easily capture these patterns. It may lead to some biases related to sensitive user attributes in the recommendation results, e.g., always recommending sports news to male users, which is unfair since users may… 

Figures and Tables from this paper

Personalized News Recommendation with Knowledge-aware Interactive Matching

A knowledge-aware interactive matching method to interactively learn representations for both clicked news and candidate news by capturing their relatedness in both semantic and entities with the help of knowledge graphs is proposed.

A Survey on Adversarial Recommender Systems

The goal of this survey is to present recent advances on adversarial machine learning (AML) for the security of RS and to show another successful application of AML in generative adversarial networks (GANs) for generative applications, thanks to their ability for learning (high-dimensional) data distributions.

TFROM: A Two-sided Fairness-Aware Recommendation Model for Both Customers and Providers

The relationship between recommendation quality, customers fairness, and provider fairness, is analyzed, and a two-sided fairness-aware recommendation model (TFROM) is designed for both customers and providers.

A survey on Adversarial Recommender Systems: from Attack/Defense strategies to Generative Adversarial Networks

An exhaustive literature review of 74 articles published in major RS and ML journals and conferences is provided, to present recent advances on adversarial machine learning (AML) for the security of RS and to show another successful application of AML in generative adversarial networks (GANs) for generative applications.

A Survey on the Fairness of Recommender Systems

This survey reviews over 60 papers published in top conferences/journals and provides an elaborate taxonomy of fairness methods in the recommendation, and outlines some promising future directions on fairness in recommendation.

FairRank: Fairness-aware Single-tower Ranking Framework for News Recommendation

This paper proposes FairRank, a fairness-aware single-tower ranking framework for news recommendation to use a shared candidate-aware user model to match user interest with a real displayed candidate news and a random news, and applies adversarial learning to both of them to reduce the biases brought by sensitive user attributes.

Semi-FairVAE: Semi-supervised Fair Representation Learning with Adversarial Variational Autoencoder

A bias-aware model to capture inherent bias information on sensitive attributes by accurately predicting sensitive attributes from input data, and a bias-free model to learn debi-ased fair representations by using adversarial learning to remove bias information from them are used.

Personalized News Recommendation: Methods and Challenges

A novel perspective to understand personalized news recommendation based on its core problems and the associated techniques and challenges is proposed and proposed instead of following the conventional taxonomy of news recommendation methods.

Uni-FedRec: A Unified Privacy-Preserving News Recommendation Framework for Model Training and Online Serving

A news recommendation framework which can utilize user data locally stored in user clients to train models and serve users in a privacy-preserving way, and an interest decomposer-aggregator method with perturbation noise to better protect private user information encoded in user interest representations.

A Comprehensive Survey on Trustworthy Recommender Systems

WENQI FAN, The Hong Kong Polytechnic University, Hong Kong XIANGYU ZHAO∗, City University of Hong Kong, Hong Kong XIAO CHEN, The Hong Kong Polytechnic University, Hong Kong JINGRAN SU, The Hong Kong



Neural News Recommendation with Attentive Multi-View Learning

A neural news recommendation approach which can learn informative representations of users and news by exploiting different kinds of news information and can effectively improve the performance of news recommendation is proposed.

A Fairness-aware Hybrid Recommender System

This paper proposes a hybrid fairness-aware recommender system that provides efficient and accurate recommendations by incorporating multiple user-user and item-item similarity measures, content, and demographic information, while addressing recommendation biases.

Neural News Recommendation with Multi-Head Self-Attention

A neural news recommendation approach with multi-head self-attentions to learn news representations from news titles by modeling the interactions between words and applies additive attention to learn more informative news and user representations by selecting important words and news.

Graph Neural News Recommendation with Long-term and Short-term Interest Modeling

NPA: Neural News Recommendation with Personalized Attention

A neural news recommendation model with personalized attention (NPA) which exploits the embedding of user ID to generate the query vector for the word- and news-level attentions.

DAN: Deep Attention Neural Network for News Recommendation

The proposed DAN model presents to use attention-based parallel CNN for aggregating user’s interest features and attention- based RNN for capturing richer hidden sequential features of user's clicks, and combines these features for new recommendation.

Personalized fairness-aware re-ranking for microlending

A Fairness-Aware Re-ranking (FAR) algorithm to balance ranking quality and borrower-side fairness, which can significantly promote fairness with little sacrifice in accuracy, and be attentive to individual lender preference on loan diversity.

Fairness-Aware Tensor-Based Recommendation

A novel fairness-aware tensor recommendation framework that is designed to maintain quality while dramatically improving fairness and enhances recommendation fairness while preserving recommendation quality in comparison with state-of-the-art alternatives is proposed.

Neural Gender Prediction from News Browsing Data

A neural gender prediction approach based on the news browsing data of users is proposed by incorporating different components of browsed news as different views of users to learn unified user representations for gender prediction.

Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Search

This work presents a framework for quantifying and mitigating algorithmic bias in mechanisms designed for ranking individuals, typically used as part of web-scale search and recommendation systems, and is the first large-scale deployed framework for ensuring fairness in the hiring domain.