• Home
  • Search
  • Constrained Off-policy Learning over Heterogeneous Information for Fairness-aware Recommendation
  • Cite Icon4
  • https://doi.org/10.1145/3629172Copy DOI Icon

Constrained Off-policy Learning over Heterogeneous Information for Fairness-aware Recommendation

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Fairness-aware recommendation eliminates discrimination issues to build trustworthy recommendation systems. Existing fairness-aware approaches ignore accounting for rich user and item attributes and thus cannot capture the impact of attributes on affecting recommendation fairness. These real-world attributes severely cause unfair recommendations by favoring items with popular attributes, leading to item exposure unfairness in recommendations. Moreover, existing approaches mostly mitigate unfairness for static recommendation models, e.g., collaborative filtering. Static models can not handle dynamic user interactions with the system that reflect users’ preferences shift through time. Thus, static models are limited in their ability to adapt to user behavior shifts to gain long-run user satisfaction. As user and item attributes are largely involved in modern recommenders and user interactions are naturally dynamic, it is essential to develop a novel method that eliminates unfairness caused by attributes meanwhile embrace the dynamic modeling of user behavior shifts. In this article, we propose Constrained Off-policy Learning over Heterogeneous Information for Fairness-aware Recommendation (Fair-HINpolicy) , which uses recent advances in context-aware off-policy learning to produce fairness-aware recommendations with rich attributes from a Heterogeneous Information Network. In particular, we formulate the off-policy learning as a Constrained Markov Decision Process (CMDP) by dynamically constraining the fairness of item exposure at each iteration. We also design an attentive action sampling to reduce the search space for off-policy learning. Our solution adaptively receives HIN-augmented corrections for counterfactual risk minimization, and ultimately yields an effective policy that maximizes long-term user satisfaction. We extensively evaluate our method through simulations on large-scale real-world datasets, obtaining favorable results compared with state-of-the-art methods.

Similar Papers
  • Research Article
  • Citations16

An improved similarity calculation method for collaborative filtering- based recommendation, considering neighbor’s liking and disliking of categorical attributes of items

  • Feb 17, 2019
  • Journal of Information and Optimization Sciences
  • Pradeep Kumar Singh +2
  • Book Chapter

Recommendation with Heterogeneous Information

  • Jan 01, 2017
  • Chuan Shi +1
  • Research Article
  • Citations72

Multi-Task Learning for Recommendation Over Heterogeneous Information Network

  • May 21, 2020
  • IEEE Transactions on Knowledge and Data Engineering
  • Hui Li +3
  • Conference Article
  • Citations3

Comparative analysis of similarity measures in Heterogeneous Information Network

  • Jan 01, 2017
  • Vaishali Patil +2
  • Research Article
  • Citations25

Scalable Representation Learning for Dynamic Heterogeneous Information Networks via Metagraphs

  • Mar 09, 2022
  • ACM Transactions on Information Systems
  • Yang Fang +4
  • Book Chapter
  • Citations10

Meta-Graph Based Attention-Aware Recommendation over Heterogeneous Information Networks

  • Jan 01, 2019
  • Feifei Dai +5
  • Conference Article
  • Citations6

A Human-in-the-loop Approach to Social Behavioral Targeting

  • Apr 01, 2021
  • Jingru Yang +6
  • Research Article
  • Citations10

Joint latent factors and attributes to discover interpretable preferences in recommendation

  • Jul 19, 2019
  • Information Sciences
  • Cong Zou +1
  • Book Chapter

A Meta Graph-Based Top-k Similarity Measure for Heterogeneous Information Networks

  • Jan 01, 2020
  • Xiangtao Chen +4
  • Research Article
  • Citations158

HINGRL: predicting drug-disease associations with graph representation learning on heterogeneous information networks.

  • Dec 09, 2021
  • Briefings in Bioinformatics
  • Bo-Wei Zhao +4
  • Book Chapter

Network Representation Learning Based Extended Matrix Factorization for Recommendation

  • Jan 01, 2020
  • Jinmao Xu +3
  • Research Article
  • Citations20

Exploring heterogeneous information networks and random walk with restart for academic search

  • Aug 26, 2012
  • Knowledge and Information Systems
  • Meng-Fen Chiang +4
  • Research Article
  • Citations7

Toward Tweet Entity Linking With Heterogeneous Information Networks

  • Mar 24, 2021
  • IEEE Transactions on Knowledge and Data Engineering
  • Wei Shen +5
  • Conference Article
  • Citations158

Naïve filterbots for robust cold-start recommendations

  • Aug 20, 2006
  • Seung-Taek Park +4
  • Research Article
  • Citations4

Protein Complex Identification Based on Heterogeneous Protein Information Network.

  • Sep 01, 2023
  • Journal of Computational Biology
  • Peixuan Zhou +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.