Barlow Twins for Sequential Recommendation

TL;DR

This paper introduces BT-SR, a noncontrastive self-supervised learning framework for sequential recommendation that improves accuracy, longtail item coverage, and calibration without negative sampling or artificial augmentations.

Contribution

BT-SR uniquely applies the Barlow Twins principle to sequential recommendation, eliminating the need for negative sampling and enhancing diversity and accuracy.

Findings

BT-SR outperforms existing methods on five benchmarks.

It improves longtail item coverage and recommendation calibration.

A single hyperparameter controls the accuracy-diversity tradeoff.

Abstract

Sequential recommendation models must navigate sparse interaction data popularity bias and conflicting objectives like accuracy versus diversity While recent contrastive selfsupervised learning SSL methods offer improved accuracy they come with tradeoffs large batch requirements reliance on handcrafted augmentations and negative sampling that can reinforce popularity bias In this paper we introduce BT-SR a novel noncontrastive SSL framework that integrates the Barlow Twins redundancyreduction principle into a Transformerbased nextitem recommender BTSR learns embeddings that align users with similar shortterm behaviors while preserving longterm distinctionswithout requiring negative sampling or artificial perturbations This structuresensitive alignment allows BT-SR to more effectively recognize emerging user intent and mitigate the influence of noisy historical context Our experiments on five public benchmarks demonstrate that BTSR consistently improves nextitem prediction accuracy and significantly enhances longtail item coverage and recommendation calibration Crucially we show that a single hyperparameter can control the accuracydiversity tradeoff enabling practitioners to adapt recommendations to specific application needs