# eSASRec: Enhancing Transformer-based Recommendations in a Modular Fashion

arXiv: https://arxiv.org/abs/2508.06450 · HTML: https://mlsanity.com/paper/2508.06450/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 40 references that are in the map.
- First posted on arXiv 8 Aug 2025.

## Builds on (most cited first, 24 of 24)

- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization](https://mlsanity.com/paper/2008.07873/) (2020)
- [Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations](https://mlsanity.com/paper/2402.17152/) (2024)
- [Neural Collaborative Filtering vs. Matrix Factorization Revisited](https://mlsanity.com/paper/2005.09683/) (2020)
- [Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation](https://mlsanity.com/paper/2110.05730/) (2021)
- [A Critical Study on Data Leakage in Recommender System Offline Evaluation](https://mlsanity.com/paper/2010.11060/) (2020)
- [On the Effectiveness of Sampled Softmax Loss for Item Recommendation](https://mlsanity.com/paper/2201.02327/) (2022)
- [Contrastive Learning for Debiased Candidate Generation in Large-Scale Recommender Systems](https://mlsanity.com/paper/2005.12964/) (2020)
- [gSASRec: Reducing Overconfidence in Sequential Recommendation Trained with Negative Sampling](https://mlsanity.com/paper/2308.07192/) (2023)
- [Lightweight Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/2108.11333/) (2021)
- [A Systematic Review and Replicability Study of BERT4Rec for Sequential Recommendation](https://mlsanity.com/paper/2207.07483/) (2022)
- [Widespread Flaws in Offline Evaluation of Recommender Systems](https://mlsanity.com/paper/2307.14951/) (2023)
- [Empirical Analysis of Session-Based Recommendation Algorithms](https://mlsanity.com/paper/1910.12781/) (2019)
- [Uniform Sequence Better: Time Interval Aware Data Augmentation for Sequential Recommendation](https://mlsanity.com/paper/2212.08262/) (2022)
- [Scalable Cross-Entropy Loss for Sequential Recommendations with Large Item Catalogs](https://mlsanity.com/paper/2409.18721/) (2024)
- [Contrastive Learning with Bidirectional Transformers for Sequential Recommendation](https://mlsanity.com/paper/2208.03895/) (2022)
- [Enhancing High-order Interaction Awareness in LLM-based Recommender Model](https://mlsanity.com/paper/2409.19979/) (2024)
- [Curse of "Low" Dimensionality in Recommender Systems](https://mlsanity.com/paper/2305.13597/) (2023)
- [Positional encoding is not the same as context: A study on positional encoding for sequential recommendation](https://mlsanity.com/paper/2405.10436/) (2024)
- [Revisiting BPR: A Replicability Study of a Common Recommender System Baseline](https://mlsanity.com/paper/2409.14217/) (2024)
- [Modeling Online Behavior in Recommender Systems: The Importance of Temporal Context](https://mlsanity.com/paper/2009.08978/) (2020)
- [MTS Kion Implicit Contextualised Sequential Dataset for Movie Recommendation](https://mlsanity.com/paper/2209.00325/) (2022)

## Built on by (most cited first, 3 of 3)

- [SplitLight: An Exploratory Toolkit for Recommender Systems Datasets and Splits](https://mlsanity.com/paper/2602.19339/) (2026)
- [Pre-trained LLMs Meet Sequential Recommenders: Efficient User-Centric Knowledge Distillation](https://mlsanity.com/paper/2604.21536/) (2026)
- [SISA-Rec: A Semantically Integrated Sequential Recommender with Contrastive Alignment](https://mlsanity.com/paper/2607.11168/) (2026)

## Abstract (arXiv)

Since their introduction, Transformer-based models, such as SASRec and BERT4Rec, have become common baselines for sequential recommendations, surpassing earlier neural and non-neural methods. A number of following publications have shown that the effectiveness of these models can be improved by, for example, slightly updating the architecture of the Transformer layers, using better training objectives, and employing improved loss functions. However, the additivity of these modular improvements has not been systematically benchmarked - this is the gap we aim to close in this paper. Through our experiments, we identify a very strong model that uses SASRec's training objective, LiGR Transformer layers, and Sampled Softmax Loss. We call this combination eSASRec (Enhanced SASRec). While we primarily focus on realistic, production-like evaluation, in our preliminarily study we find that common academic benchmarks show eSASRec to be 23% more effective compared to the most recent state-of-the-art models, such as ActionPiece. In our main production-like benchmark, eSASRec resides on the Pareto frontier in terms of the accuracy-coverage tradeoff (alongside the recent industrial models HSTU and FuXi. As the modifications compared to the original SASRec are relatively straightforward and no extra features are needed (such as timestamps in HSTU), we believe that eSASRec can be easily integrated into existing recommendation pipelines and can can serve as a strong yet very simple baseline for emerging complicated algorithms. To facilitate this, we provide the open-source implementations for our models and benchmarks in repository https://github.com/blondered/transformer_benchmark