Scaling Session-Based Transformer Recommendations using Optimized Negative Sampling and Loss Functions

TL;DR

TRON is a scalable session-based Transformer recommender that uses optimized negative sampling and listwise loss functions to improve recommendation accuracy and training efficiency, demonstrated by large-scale e-commerce dataset evaluations and an A/B test.

Contribution

This paper introduces TRON, a novel Transformer-based recommender that incorporates top-k negative sampling and listwise loss functions for enhanced scalability and performance.

Findings

TRON outperforms existing models in recommendation quality.

TRON maintains training speeds comparable to SASRec.

A/B testing shows an 18.14% increase in click-through rate.

Abstract

This work introduces TRON, a scalable session-based Transformer Recommender using Optimized Negative-sampling. Motivated by the scalability and performance limitations of prevailing models such as SASRec and GRU4Rec+, TRON integrates top-k negative sampling and listwise loss functions to enhance its recommendation accuracy. Evaluations on relevant large-scale e-commerce datasets show that TRON improves upon the recommendation quality of current methods while maintaining training speeds similar to SASRec. A live A/B test yielded an 18.14% increase in click-through rate over SASRec, highlighting the potential of TRON in practical settings. For further research, we provide access to our source code at https://github.com/otto-de/TRON and an anonymized dataset at https://github.com/otto-de/recsys-dataset.