A Fairness-aware Hybrid Recommender System

Abstract

Recommender systems are used in variety of domains affecting people's lives. This has raised concerns about possible biases and discrimination that such systems might exacerbate. There are two primary kinds of biases inherent in recommender systems: observation bias and bias stemming from imbalanced data. Observation bias exists due to a feedback loop which causes the model to learn to only predict recommendations similar to previous ones. Imbalance in data occurs when systematic societal, historical, or other ambient bias is present in the data. In this paper, we address both biases by proposing a hybrid fairness-aware recommender system. Our model provides efficient and accurate recommendations by incorporating multiple user-user and item-item similarity measures, content, and demographic information, while addressing recommendation biases. We implement our model using a powerful and expressive probabilistic programming language called probabilistic soft logic. We experimentally evaluate our approach on a popular movie recommendation dataset, showing that our proposed model can provide more accurate and fairer recommendations, compared to a state-of-the art fair recommender system.

References in corpus (3)

• Beyond Parity: Fairness Objectives for Collaborative Filtering
• Multisided Fairness for Recommendation
• Online Interactive Collaborative Filtering Using Multi-Armed Bandit with Dependent Arms

Cited by in corpus (11)

• A Survey on the Fairness of Recommender Systems
• EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks
• FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings
• Deep Learning on Knowledge Graph for Recommender System: A Survey
• Towards Fair Personalization by Avoiding Feedback Loops
• FairRec: Fairness-aware News Recommendation with Decomposed Adversarial Learning
• Recommender Systems Fairness Evaluation via Generalized Cross Entropy
• Fairness Through Regularization for Learning to Rank
• What is fair? Exploring the artists' perspective on the fairness of music streaming platforms
• Learning Fairness-aware Relational Structures
• HyperFair: A Soft Approach to Integrating Fairness Criteria