Top Rank Optimization in Linear Time

TL;DR

This paper introduces TopPush, a highly efficient bipartite ranking method that optimizes accuracy at the top with linear time complexity, providing competitive results and significantly faster computation.

Contribution

The paper presents TopPush, a novel linear-time algorithm for top-ranked bipartite ranking that improves efficiency while maintaining competitive accuracy.

Findings

TopPush achieves 10-100 times faster training than existing methods.

It provides a theoretical bound on generalization error for top-ranked instances.

Empirical results show competitive performance with state-of-the-art approaches.

Abstract

Bipartite ranking aims to learn a real-valued ranking function that orders positive instances before negative instances. Recent efforts of bipartite ranking are focused on optimizing ranking accuracy at the top of the ranked list. Most existing approaches are either to optimize task specific metrics or to extend the ranking loss by emphasizing more on the error associated with the top ranked instances, leading to a high computational cost that is super-linear in the number of training instances. We propose a highly efficient approach, titled TopPush, for optimizing accuracy at the top that has computational complexity linear in the number of training instances. We present a novel analysis that bounds the generalization error for the top ranked instances for the proposed approach. Empirical study shows that the proposed approach is highly competitive to the state-of-the-art approaches and is 10-100 times faster.