Learning-to-rank (LTR) methods have traditionally been limited to discriminative machine learning approaches that model the probability of the document being relevant to the query given some feature representation of the query-document pair. We propose an alternative denoising diffusion-based generative approach to LTR that instead models the full joint distribution over features and relevance labels. While in discriminative LTR, an over-parameterized ranking model may find different ways to fit the training data, we posit that candidate solutions that can explain the full data distribution under the generative setting maybe better at estimating relevance. Thus, we propose DiffusionRank that extends TabDiff, an existing diffusion model for tabular datasets, to create generative alternatives to classical discriminative pointwise and pairwise LTR objectives. Our work demonstrates improvements from DiffusionRank over discriminative counterparts on four standard LTR datasets and points to a rich space for future exploration to leverage ongoing advancements in deep generative models for LTR. Our code is publicly available at https://github.com/sadjadeb/DiffusionRank.

翻译：学习排序方法（LTR）传统上局限于判别式机器学习方法，这类方法通过查询-文档对的特征表示来建模文档与查询相关性的概率。我们提出了一种基于去噪扩散的生成式替代方案来构建LTR模型，该方案直接对特征与相关性标签的完整联合分布进行建模。在判别式LTR中，过参数化的排序模型可能以不同方式拟合训练数据，而我们假设在生成式框架下能够解释完整数据分布的候选解可能更擅长评估相关性。为此，我们提出DiffusionRank方法，将现有表格数据扩散模型TabDiff扩展为经典判别式逐点与逐对LTR目标的生成式替代方案。实验表明，在四个标准LTR数据集上，DiffusionRank相较于判别式对应方法取得了性能提升，并为利用深度生成模型在LTR领域的最新进展开辟了丰富的探索空间。我们的代码已开源在https://github.com/sadjadeb/DiffusionRank。