arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.00979cs.IRcs.LG
收藏

利用增强的损失函数改进序列推荐模型

Improving Sequential Recommendation Models with an Enhanced Loss Function

Xiamen University(厦门大学)

Fangyu Li, Shenbao Yu, Feng Zeng, Fang Yang

AI总结:

本文分析了序列推荐中常用损失函数的优缺点,提出一种结合各优势的改进损失函数,在多个开源库上的实验表明该函数显著提升了GRU4Rec、SASRec等模型的性能,并使改进的SASRec基准在多个数据集上优于或接近BERT4Rec。

摘要:

近年来,人们对基准测试序列推荐模型以及复现和改进现有模型的兴趣日益浓厚。例如,Rendle等人通过调整参数和超参数改进了矩阵分解模型。Petrov和Macdonald开发了BERT4Rec的一种更高效、更有效的实现,解决了先前工作中BERT4Rec和SASRec之间性能比较的不一致问题。特别是,BERT4Rec和SASRec共享相似的网络结构,主要区别在于它们的训练目标/损失函数。因此,我们分析了序列推荐中常用损失函数的优缺点,并提出了一种利用其优势的改进损失函数。我们在两个有影响力的开源库上进行了广泛的实验,结果表明,我们改进的损失函数显著增强了GRU4Rec、SASRec、SR-GNN和S3Rec模型的性能,大幅提升了它们的基准。此外,改进后的SASRec基准在ML-1M和Beauty数据集上优于BERT4Rec,并在ML-20M和Steam数据集上取得了与BERT4Rec相似的结果。我们还复现了BERT4Rec模型在Beauty数据集上的结果。最后,我们通过实验对我们改进的损失函数的有效性提供了全面的解释。我们的代码已在https://github.com/Li-fAngyU/sequential_rec公开发布。

英文摘要:

There has been a growing interest in benchmarking sequential recommendation models and reproducing/improving existing models. For example, Rendle et al. improved matrix factorization models by tuning their parameters and hyperparameters. Petrov and Macdonald developed a more efficient and effective implementation of BERT4Rec, which resolved inconsistencies in performance comparison between BERT4Rec and SASRec in previous works. In particular, BERT4Rec and SASRec share a similar network structure, with the main difference lying in their training objective/loss function. Therefore, we analyzed the advantages and disadvantages of commonly used loss functions in sequential recommendation and proposed an improved loss function that leverages their strengths. We conduct extensive experiments on two influential open-source libraries, and the results demonstrate that our improved loss function significantly enhances the performance of GRU4Rec, SASRec, SR-GNN, and S3Rec models, improving their benchmarks significantly. Furthermore, the improved SASRec benchmark outperforms BERT4Rec on the ML-1M and Beauty datasets and achieves similar results to BERT4Rec on the ML-20M and Steam datasets. We also reproduce the results of the BERT4Rec model on the Beauty dataset. Finally, we provide a comprehensive explanation of the effectiveness of our improved loss function through experiments. Our code is publicly available at https://github.com/Li-fAngyU/sequential_rec.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑