Poster
Hybrid-MST: A Hybrid Active Sampling Strategy for Pairwise Preference Aggregation
JING LI · Rafal Mantiuk · Junle Wang · Suiyi Ling · Patrick Le Callet
Room 517 AB #126
Keywords: [ Information Retrieval ] [ Recommender Systems ] [ Bayesian Theory ] [ Active Learning ] [ Ranking and Preference Learning ]
In this paper we present a hybrid active sampling strategy for pairwise preference aggregation, which aims at recovering the underlying rating of the test candidates from sparse and noisy pairwise labeling. Our method employs Bayesian optimization framework and Bradley-Terry model to construct the utility function, then to obtain the Expected Information Gain (EIG) of each pair. For computational efficiency, Gaussian-Hermite quadrature is used for estimation of EIG. In this work, a hybrid active sampling strategy is proposed, either using Global Maximum (GM) EIG sampling or Minimum Spanning Tree (MST) sampling in each trial, which is determined by the test budget. The proposed method has been validated on both simulated and real-world datasets, where it shows higher preference aggregation ability than the state-of-the-art methods.
Live content is unavailable. Log in and register to view live content