beeFormer: Bridging the Gap Between Semantic and Interaction Similarity in Recommender Systems

TL;DR

beeFormer is a novel framework that trains sentence Transformers with interaction data, enabling transfer learning across datasets and domains, and outperforming existing semantic similarity models and collaborative filtering methods in recommender systems.

Contribution

It introduces a new training approach for sentence Transformers using interaction data, facilitating universal, domain-agnostic models for recommender systems.

Findings

Models trained with beeFormer outperform traditional semantic similarity Transformers.

Training on multiple datasets enables knowledge transfer and domain generalization.

The approach supports the development of universal recommender models.

Abstract

Recommender systems often use text-side information to improve their predictions, especially in cold-start or zero-shot recommendation scenarios, where traditional collaborative filtering approaches cannot be used. Many approaches to text-mining side information for recommender systems have been proposed over recent years, with sentence Transformers being the most prominent one. However, these models are trained to predict semantic similarity without utilizing interaction data with hidden patterns specific to recommender systems. In this paper, we propose beeFormer, a framework for training sentence Transformer models with interaction data. We demonstrate that our models trained with beeFormer can transfer knowledge between datasets while outperforming not only semantic similarity sentence Transformers but also traditional collaborative filtering methods. We also show that training on multiple datasets from different domains accumulates knowledge in a single model, unlocking the possibility of training universal, domain-agnostic sentence Transformer models to mine text representations for recommender systems. We release the source code, trained models, and additional details allowing replication of our experiments at https://github.com/recombee/beeformer.