Bounded-Abstention Pairwise Learning to Rank

TL;DR

This paper introduces a novel abstention method for pairwise learning-to-rank systems, enabling decision deferment in uncertain cases, with theoretical insights, a practical algorithm, and empirical validation across datasets.

Contribution

It provides the first theoretical framework and a model-agnostic algorithm for abstention in pairwise ranking, extending abstention concepts beyond classification.

Findings

The proposed method effectively reduces risky decisions in ranking tasks.

Empirical results show improved performance with abstention across multiple datasets.

Theoretical analysis characterizes optimal abstention strategies in ranking.

Abstract

Ranking systems influence decision-making in high-stakes domains like health, education, and employment, where they can have substantial economic and social impacts. This makes the integration of safety mechanisms essential. One such mechanism is $\textit{abstention}$, which enables algorithmic decision-making system to defer uncertain or low-confidence decisions to human experts. While abstention have been predominantly explored in the context of classification tasks, its application to other machine learning paradigms remains underexplored. In this paper, we introduce a novel method for abstention in pairwise learning-to-rank tasks. Our approach is based on thresholding the ranker's conditional risk: the system abstains from making a decision when the estimated risk exceeds a predefined threshold. Our contributions are threefold: a theoretical characterization of the optimal abstention strategy, a model-agnostic, plug-in algorithm for constructing abstaining ranking models, and a comprehensive empirical evaluations across multiple datasets, demonstrating the effectiveness of our approach.