Graph-based rank aggregation: a deep-learning approach

Abstract

Purpose This study aims to introduce a novel rank aggregation algorithm that leverages graph theory and deep-learning to improve the accuracy and relevance of aggregated rankings in metasearch scenarios, particularly when faced with inconsistent and low-quality rank lists. By strategically selecting a subset of base rankers, the algorithm enhances the quality of the aggregated ranking while using only a subset of base rankers. Design/methodology/approach The proposed algorithm leverages a graph-based model to represent the interrelationships between base rankers. By applying Spectral clustering, the algorithm identifies a subset of top-performing base rankers based on their retrieval effectiveness. These selected rankers are then integrated into a sequential deep-learning model to estimate relevance labels for query-document pairs. Findings Empirical evaluation on the MQ2007-agg and MQ2008-agg data sets demonstrates the substantial performance gains achieved by the proposed algorithm compared to baseline methods, with an average improvement of 8.7% in MAP and 11.9% in NDCG@1. The algorithm’s effectiveness can be attributed to its ability to effectively integrate diverse perspectives from base rankers and capture complex relationships within the data. Originality/value This research presents a novel approach to rank aggregation that integrates graph theory and deep-learning. The author proposes a graph-based model to select the most effective subset for metasearch applications by constructing a similarity graph of base rankers. This innovative method addresses the challenges posed by inconsistent and low-quality rank lists, offering a unique solution to the problem.