A Systematic Replicability and Comparative Study of BSARec and SASRec for Sequential Recommendation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: D'Ercoli, Chiara, Di Teodoro, Giulia, Siciliano, Federico
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916796993372160
author D'Ercoli, Chiara
Di Teodoro, Giulia
Siciliano, Federico
author_facet D'Ercoli, Chiara
Di Teodoro, Giulia
Siciliano, Federico
contents This study aims at comparing two sequential recommender systems: Self-Attention based Sequential Recommendation (SASRec), and Beyond Self-Attention based Sequential Recommendation (BSARec) in order to check the improvement frequency enhancement - the added element in BSARec - has on recommendations. The models in the study, have been re-implemented with a common base-structure from EasyRec, with the aim of obtaining a fair and reproducible comparison. The results obtained displayed how BSARec, by including bias terms for frequency enhancement, does indeed outperform SASRec, although the increases in performance obtained, are not as high as those presented by the authors. This work aims at offering an overview on existing methods, and most importantly at underlying the importance of implementation details for performance comparison.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14692
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Systematic Replicability and Comparative Study of BSARec and SASRec for Sequential Recommendation
D'Ercoli, Chiara
Di Teodoro, Giulia
Siciliano, Federico
Information Retrieval
This study aims at comparing two sequential recommender systems: Self-Attention based Sequential Recommendation (SASRec), and Beyond Self-Attention based Sequential Recommendation (BSARec) in order to check the improvement frequency enhancement - the added element in BSARec - has on recommendations. The models in the study, have been re-implemented with a common base-structure from EasyRec, with the aim of obtaining a fair and reproducible comparison. The results obtained displayed how BSARec, by including bias terms for frequency enhancement, does indeed outperform SASRec, although the increases in performance obtained, are not as high as those presented by the authors. This work aims at offering an overview on existing methods, and most importantly at underlying the importance of implementation details for performance comparison.
title A Systematic Replicability and Comparative Study of BSARec and SASRec for Sequential Recommendation
topic Information Retrieval
url https://arxiv.org/abs/2506.14692