RAT: Retrieval-Augmented Transformer for Click-Through Rate Prediction
This addresses a fundamental task for web applications by enhancing CTR prediction through cross-sample relationships, though it appears incremental by building on existing Transformer methods.
The paper tackles the problem of click-through rate prediction by proposing a Retrieval-Augmented Transformer (RAT) to model both intra- and cross-sample feature interactions, achieving improved prediction performance as validated on real-world datasets.
Predicting click-through rates (CTR) is a fundamental task for Web applications, where a key issue is to devise effective models for feature interactions. Current methodologies predominantly concentrate on modeling feature interactions within an individual sample, while overlooking the potential cross-sample relationships that can serve as a reference context to enhance the prediction. To make up for such deficiency, this paper develops a Retrieval-Augmented Transformer (RAT), aiming to acquire fine-grained feature interactions within and across samples. By retrieving similar samples, we construct augmented input for each target sample. We then build Transformer layers with cascaded attention to capture both intra- and cross-sample feature interactions, facilitating comprehensive reasoning for improved CTR prediction while retaining efficiency. Extensive experiments on real-world datasets substantiate the effectiveness of RAT and suggest its advantage in long-tail scenarios. The code has been open-sourced at \url{https://github.com/YushenLi807/WWW24-RAT}.