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

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.

Accepted at the Seventeenth ACM Conference on Recommender Systems (RecSys '23)

Cited by in corpus (9)

• Scalable Cross-Entropy Loss for Sequential Recommendations with Large Item Catalogs
• RECE: Reduced Cross-Entropy Loss for Large-Catalogue Sequential Recommenders
• RePlay: a Recommendation Framework for Experimentation and Production Use
• Negative Feedback for Music Personalization
• Semantic IDs for Music Recommendation
• Pareto Front Approximation for Multi-Objective Session-Based Recommender Systems
• Autoregressive Generation Strategies for Top-K Sequential Recommendations
• Industry Insights from Comparing Deep Learning and GBDT Models for E-Commerce Learning-to-Rank
• Identifying Offline Metrics that Predict Online Impact: A Pragmatic Strategy for Real-World Recommender Systems