Fair Link Prediction with Multi-Armed Bandit Algorithms

Weixiang Wang, Sucheta Soundarajan

Research output: Chapter in Book/Entry/PoemConference contribution


Recommendation systems have been used in many domains, and in recent years, ethical problems associated with such systems have gained serious attention. The problem of unfairness in friendship or link recommendation systems in social networks has begun attracting attention, as such unfairness can cause problems like segmentation and echo chambers. One challenge in this problem is that there are many fairness metrics for networks, and existing methods only consider the improvement of a single specific fairness indicator [16, 17, 20]. In this work, we model the fair link prediction problem as a multi-armed bandit problem. We propose FairLink, a multi-armed bandit based framework that predicts new edges that are both accurate and well-behaved with respect to a fairness property of choice. This method allows the user to specify the desired fairness metric. Experiments on five real-world datasets show that FairLink can achieve a significant fairness improvement as compared to a standard recommendation algorithm, with only a small reduction in accuracy.

Original languageEnglish (US)
Title of host publicationWebSci 2023 - Proceedings of the 15th ACM Web Science Conference
PublisherAssociation for Computing Machinery
Number of pages10
ISBN (Electronic)9798400700897
StatePublished - Apr 30 2023
Event15th ACM Web Science Conference, WebSci 2023 - Austin, United States
Duration: Apr 30 2023May 1 2023

Publication series

NameACM International Conference Proceeding Series


Conference15th ACM Web Science Conference, WebSci 2023
Country/TerritoryUnited States


  • fairness
  • link prediction
  • social networks

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software


Dive into the research topics of 'Fair Link Prediction with Multi-Armed Bandit Algorithms'. Together they form a unique fingerprint.

Cite this