# On the Efficiency of Sequentially Aware Recommender Systems: Cotten4Rec

Source: [On the Efficiency of Sequentially Aware Recommender Systems: Cotten4Rec](<https://www.sota2.com/research/paper/69896a3ac97a0b3e3b5dc682>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-10T05:00:14.833Z

Authors: Shankar Veludandi, Gulrukh Kurdistan, Uzma Mushtaque

Published: 2026-02-06T18:30:23.000Z

## Abstract

Sequential recommendation (SR) models predict a user's next interaction by modeling their historical behaviors. Transformer-based SR methods, notably BERT4Rec, effectively capture these patterns but incur significant computational overhead due to extensive intermediate computations associated with Softmax-based attention. We propose Cotten4Rec, a novel SR model utilizing linear-time cosine similarity attention, implemented through a single optimized compute unified device architecture (CUDA) kernel. By minimizing intermediate buffers and kernel-launch overhead, Cotten4Rec substantially reduces resource usage compared to BERT4Rec and the linear-attention baseline, LinRec, especially for datasets with moderate sequence lengths and vocabulary sizes. Evaluations across three benchmark datasets confirm that Cotten4Rec achieves considerable reductions in memory and runtime with minimal compromise in recommendation accuracy, demonstrating Cotten4Rec's viability as an efficient alternative for practical, large-scale sequential recommendation scenarios where computational resources are critical.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Sequential Recommendation on Beauty (Ranking and Resource Usage)](<https://www.sota2.com/research/sota/sequential-recommendation-on-beauty-ranking-and-resource-usage.md>): Sequential Recommendation; Beauty; Memory (MB): 4094.

- [Sequential Recommendation on ML-20M](<https://www.sota2.com/research/sota/sequential-recommendation-on-ml-20m.md>): Sequential Recommendation; ML-20M; NDCG@10: 0.77.

- [Sequential Recommendation on ML-1M](<https://www.sota2.com/research/sota/sequential-recommendation-on-ml-1m.md>): Sequential Recommendation; ML 1M; NDCG@10: 0.38.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2602.06935>)

[PDF](<https://arxiv.org/pdf/2602.06935.pdf>)