Debias the Black-box: A Fair Ranking Framework via Knowledge Distillation

TL;DR

This paper introduces a knowledge distillation-based framework that significantly reduces model size and enhances fairness in deep neural network-based information retrieval systems, maintaining high recommendation accuracy.

Contribution

It presents a novel fair ranking framework using knowledge distillation to improve fairness and reduce model complexity in deep neural retrieval models.

Findings

Model size reduced to 1% of original

Fairness improved by 15% to 46%

High recommendation effectiveness maintained

Abstract

Deep neural networks can capture the intricate interaction history information between queries and documents, because of their many complicated nonlinear units, allowing them to provide correct search recommendations. However, service providers frequently face more complex obstacles in real-world circumstances, such as deployment cost constraints and fairness requirements. Knowledge distillation, which transfers the knowledge of a well-trained complex model (teacher) to a simple model (student), has been proposed to alleviate the former concern, but the best current distillation methods focus only on how to make the student model imitate the predictions of the teacher model. To better facilitate the application of deep models, we propose a fair information retrieval framework based on knowledge distillation. This framework can improve the exposure-based fairness of models while considerably decreasing model size. Our extensive experiments on three huge datasets show that our proposed framework can reduce the model size to a minimum of 1% of its original size while maintaining its black-box state. It also improves fairness performance by 15%~46% while keeping a high level of recommendation effectiveness.