Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity
This addresses a real-world challenge in search and recommendation systems where labeled data is scarce but unlabeled data is abundant, offering a practical improvement over traditional methods.
The paper tackles the problem of tabular Learning-to-Rank under label scarcity, showing that pretrained deep learning models outperform Gradient Boosted Decision Trees by up to 38% in ranking metrics, including on outlier data.
On tabular data, a significant body of literature has shown that current deep learning (DL) models perform at best similarly to Gradient Boosted Decision Trees (GBDTs), while significantly underperforming them on outlier data. However, these works often study idealized problem settings which may fail to capture complexities of real-world scenarios. We identify a natural tabular data setting where DL models can outperform GBDTs: tabular Learning-to-Rank (LTR) under label scarcity. Tabular LTR applications, including search and recommendation, often have an abundance of unlabeled data, and scarce labeled data. We show that DL rankers can utilize unsupervised pretraining to exploit this unlabeled data. In extensive experiments over both public and proprietary datasets, we show that pretrained DL rankers consistently outperform GBDT rankers on ranking metrics -- sometimes by as much as 38% -- both overall and on outliers.