arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2405.11272cs.IRcs.AI
收藏

用于去噪推荐的双重校正框架

Double Correction Framework for Denoising Recommendation

School of Computer Science and Information Engineering, Hefei University of Technology(合肥工业大学计算机与信息工程学院);Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系);Institute of Dataspace, Hefei Comprehensive National Science Center(合肥综合性国家科学中心空间研究院);Department of Mathematics, University of Macau(澳门大学数学系)

Zhuangzhuang He, Yifan Wang, Yonghui Yang, Peijie Sun, Le Wu, Haoyue Bai, Jinqi Gong, Richang Hong, Min Zhang

AI总结:

针对推荐系统中隐式反馈噪声样本问题,提出双重校正框架(DCF),通过基于时间损失值的稳定样本丢弃和渐进式标签校正,在更精确去噪的同时缓解数据稀疏,实验验证了其有效性与泛化性。

摘要:

由于隐式反馈在在线服务中的可用性和普遍性,其在推荐系统中更为常用。然而,在现实世界的推荐场景中,隐式反馈通常包含噪声样本(例如误点击或非偏好行为),这会影响对用户偏好的精确学习。为了克服噪声样本问题,一种流行的解决方案是在模型训练阶段丢弃噪声样本,其依据是观察到噪声样本的训练损失高于干净样本。尽管该方法有效,但我们认为该解决方案仍有局限性:(1)高训练损失可能源于模型优化不稳定或困难样本,而不仅仅是噪声样本。(2)完全丢弃噪声样本会加剧数据稀疏性,缺乏对数据的充分利用。为解决上述局限性,我们提出了用于去噪推荐的双重校正框架(DCF),该框架包含两个校正组件,分别从更精确的样本丢弃和避免数据更稀疏的角度出发。在样本丢弃校正组件中,我们利用样本随时间的损失值来判断其是否为噪声,以提高丢弃的稳定性。我们不直接进行平均,而是使用阻尼函数来减少异常值的偏差影响。此外,由于困难样本表现出更高的方差,我们通过浓度不等式推导出损失的下界,以识别并重用困难样本。在渐进式标签校正中,我们迭代地对高确定性的噪声样本重新标注,并对其重新训练以进一步提升性能。最后,在三个数据集和四个骨干网络上的大量实验结果表明了我们所提出框架的有效性和泛化性。

英文摘要:

As its availability and generality in online services, implicit feedback is more commonly used in recommender systems. However, implicit feedback usually presents noisy samples in real-world recommendation scenarios (such as misclicks or non-preferential behaviors), which will affect precise user preference learning. To overcome the noisy samples problem, a popular solution is based on dropping noisy samples in the model training phase, which follows the observation that noisy samples have higher training losses than clean samples. Despite the effectiveness, we argue that this solution still has limits. (1) High training losses can result from model optimization instability or hard samples, not just noisy samples. (2) Completely dropping of noisy samples will aggravate the data sparsity, which lacks full data exploitation. To tackle the above limitations, we propose a Double Correction Framework for Denoising Recommendation (DCF), which contains two correction components from views of more precise sample dropping and avoiding more sparse data. In the sample dropping correction component, we use the loss value of the samples over time to determine whether it is noise or not, increasing dropping stability. Instead of averaging directly, we use the damping function to reduce the bias effect of outliers. Furthermore, due to the higher variance exhibited by hard samples, we derive a lower bound for the loss through concentration inequality to identify and reuse hard samples. In progressive label correction, we iteratively re-label highly deterministic noisy samples and retrain them to further improve performance. Finally, extensive experimental results on three datasets and four backbones demonstrate the effectiveness and generalization of our proposed framework.

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。

↑