Rate-Optimal Rank Aggregation with Private Pairwise Rankings

arXiv:2402.16792v1 Announce Type: cross
Abstract: In various real-world scenarios like recommender systems and political surveys, pairwise rankings are commonly collected and utilized for rank aggregation to obtain an overall ranking of items. However, preference rankings can reveal individuals' personal preferences, underscoring the need to protect them before releasing for downstream analysis. In this paper, we address the challenge of preserving privacy while ensuring the utility of rank aggregation based on pairwise rankings generated from the Bradley-Terry-Luce (BTL) model. Using the …

aggregation analysis arxiv can cs.cr cs.lg personal political private protect rate real recommender systems reveal stat.ml surveys systems world