On the Efficiency of Sequentially Aware Recommender Systems: Cotten4Rec

TL;DR

Cotten4Rec introduces a linear-time cosine similarity attention mechanism for sequential recommendation, significantly reducing computational resources while maintaining accuracy, making it suitable for large-scale applications.

Contribution

The paper presents Cotten4Rec, a novel SR model that employs an efficient cosine similarity attention implemented via a single CUDA kernel, reducing resource usage compared to existing transformer-based models.

Findings

Cotten4Rec reduces memory and runtime compared to BERT4Rec.

It maintains comparable recommendation accuracy across benchmark datasets.

The model is effective for large-scale, resource-constrained environments.

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.