重新审视BPR：一种常见推荐系统基线的可复现性研究
Revisiting BPR: A Replicability Study of a Common Recommender System Baseline
AI总结：
本文重新审视BPR推荐基线，发现开源实现与原论文不一致导致性能下降，并通过超参数调优证明BPR可接近甚至超越最先进方法。
摘要：
贝叶斯个性化排序（BPR）是一种基于矩阵分解的协同过滤方法，经常作为推荐系统研究的基准。然而，许多研究常常忽视BPR实现的细节，声称其在各种任务上的表现不如新提出的方法。在本文中，我们深入考察了BPR模型的特征，指出这些特征对其性能的影响，并调查了开源的BPR实现。我们的分析揭示了这些实现与原始BPR论文之间的不一致之处，导致特定实现的性能显著下降，降幅最高可达50%。此外，通过在现代评估设置下对真实世界数据集进行大量实验，我们证明，在对其超参数进行适当调优后，BPR模型在top-n推荐任务上可以达到接近最先进方法的性能水平，甚至在特定数据集上超越它们。具体而言，在Million Song Dataset上，经过超参数调优的BPR模型在使用二元相关性函数的NDCG@100指标上，以10%的优势在统计上显著优于Mult-VAE。
英文摘要：
Bayesian Personalized Ranking (BPR), a collaborative filtering approach based on matrix factorization, frequently serves as a benchmark for recommender systems research. However, numerous studies often overlook the nuances of BPR implementation, claiming that it performs worse than newly proposed methods across various tasks. In this paper, we thoroughly examine the features of the BPR model, indicating their impact on its performance, and investigate open-source BPR implementations. Our analysis reveals inconsistencies between these implementations and the original BPR paper, leading to a significant decrease in performance of up to 50% for specific implementations. Furthermore, through extensive experiments on real-world datasets under modern evaluation settings, we demonstrate that with proper tuning of its hyperparameters, the BPR model can achieve performance levels close to state-of-the-art methods on the top-n recommendation tasks and even outperform them on specific datasets. Specifically, on the Million Song Dataset, the BPR model with hyperparameters tuning statistically significantly outperforms Mult-VAE by 10% in NDCG@100 with binary relevance function.
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。
