DenoiseRank: Learning to Rank by Diffusion Models

TL;DR

DenoiseRank introduces a novel generative diffusion model approach to learning to rank, addressing the task from a new perspective and demonstrating effectiveness on benchmark datasets.

Contribution

It is the first to apply a diffusion-based generative model to the learning to rank problem, offering a new paradigm in the field.

Findings

DenoiseRank outperforms traditional models on benchmark datasets.

The diffusion approach effectively denoises labels for accurate ranking.

Provides a new benchmark for generative learning to rank methods.

Abstract

Learning to rank (LTR) is one of the core tasks in Machine Learning. Traditional LTR models have made great progress, but nearly all of them are implemented from discriminative perspective. In this paper, we aim at addressing LTR from a novel perspective, i.e., by a deep generative model. Specifically, we propose a novel denoise rank model, DenoiseRank, which noises the relevant labels in the diffusion process and denoises them on the query documents in the reverse process to accurately predict their distribution. Our model is the first to address traditional LTR from generative perspective and is a diffusion method for LTR. Our extensive experiments on benchmark datasets demonstrated the effectiveness of DenoiseRank, and we believe it provides a benchmark for generative LTR task.