Approximately optimizing NDCG using pair-wise loss

Xiao Bo Jin, Guang Gang Geng, Guo Sen Xie, Kaizhu Huang*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

10 Citations (Scopus)

Abstract

The Normalized Discounted Cumulative Gain (NDCG) is used to measure the performance of ranking algorithms. Much of the work on learning to rank by optimizing NDCG directly or indirectly is based on list-wise approaches. In our work, we approximately optimize a variant of NDCG called NDCGβ using pair-wise approaches. NDCGβ utilizes the linear discounting function. We first prove that the DCG error of NDCGβ is equal to the weighted pair-wise loss; then, on that basis, RankBoostndcg and RankSVMndcg are proposed to optimize the upper bound of the pair-wise 0–1 loss function. The experimental results from applying our approaches and ten other state-of-the-art methods to five public datasets show the superiority of the proposed methods, especially RankSVMndcg. In addition, RankBoostndcg are less influenced by the initial weight distribution.

Original languageEnglish
Pages (from-to)50-65
Number of pages16
JournalInformation Sciences
Volume453
DOIs
Publication statusPublished - Jul 2018

Keywords

  • DCG error
  • Learning to rank
  • Optimization of NDCG
  • Pair-wise method
  • Ranking loss

Fingerprint

Dive into the research topics of 'Approximately optimizing NDCG using pair-wise loss'. Together they form a unique fingerprint.

Cite this