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 2408.11372cs.IRcs.AI
收藏

用于高效多行为序列推荐的去噪预训练与定制化提示学习

Denoising Pre-Training and Customized Prompt Learning for Efficient Multi-Behavior Sequential Recommendation

University of Science and Technology of China(中国科学技术大学);SUN YAT-SEN University(中山大学);Huawei(华为)

Hao Wang, Yongqiang Han, Kefan Wang, Kai Cheng, Zhen Wang, Wei Guo, Yong Liu, Defu Lian, Enhong Chen

AI总结:

针对多行为序列推荐中计算复杂度高且数据噪声大的问题,提出DPCPL范式,通过EBM模块多尺度去噪预训练和CPL模块高效定制化提示微调,在仅需极少参数调整的情况下,于多个真实数据集上超越了最先进性能。

摘要:

在推荐系统领域,用户在与物品交互时表现出多种多样的行为。这一现象推动了学习这些行为之间隐式语义关系的研究,以提升推荐性能。然而,这些方法通常具有较高的计算复杂度。为了解决效率问题,预训练提供了一种可行的解决方案。其目标是从大量预训练数据中提取知识,并为下游任务微调模型。尽管如此,以往的预训练方法主要关注单行为数据,而多行为数据包含显著的噪声。此外,这些方法采用的完全微调策略仍然带来了相当大的计算负担。为了应对这一挑战,我们提出了DPCPL,这是首个专为多行为序列推荐定制的预训练与提示微调范式。具体而言,在预训练阶段,我们首先提出了一种新颖的Efficient Behavior Miner (EBM),用于在多个时间尺度上过滤噪声,从而促进对多行为序列上下文语义的理解。随后,我们提出使用所提出的Customized Prompt Learning (CPL)模块,以高效的方式微调预训练模型,该模块生成个性化、渐进和多样化的提示,以充分有效地发挥预训练模型的潜力。在三个真实世界数据集上的大量实验明确表明,DPCPL不仅展现出高效性和有效性,只需极少的参数调整,还在多种下游任务中超越了最先进的性能。

英文摘要:

In the realm of recommendation systems, users exhibit a diverse array of behaviors when interacting with items. This phenomenon has spurred research into learning the implicit semantic relationships between these behaviors to enhance recommendation performance. However, these methods often entail high computational complexity. To address concerns regarding efficiency, pre-training presents a viable solution. Its objective is to extract knowledge from extensive pre-training data and fine-tune the model for downstream tasks. Nevertheless, previous pre-training methods have primarily focused on single-behavior data, while multi-behavior data contains significant noise. Additionally, the fully fine-tuning strategy adopted by these methods still imposes a considerable computational burden. In response to this challenge, we propose DPCPL, the first pre-training and prompt-tuning paradigm tailored for Multi-Behavior Sequential Recommendation. Specifically, in the pre-training stage, we commence by proposing a novel Efficient Behavior Miner (EBM) to filter out the noise at multiple time scales, thereby facilitating the comprehension of the contextual semantics of multi-behavior sequences. Subsequently, we propose to tune the pre-trained model in a highly efficient manner with the proposed Customized Prompt Learning (CPL) module, which generates personalized, progressive, and diverse prompts to fully exploit the potential of the pre-trained model effectively. Extensive experiments on three real-world datasets have unequivocally demonstrated that DPCPL not only exhibits high efficiency and effectiveness, requiring minimal parameter adjustments but also surpasses the state-of-the-art performance across a diverse range of downstream tasks.

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。

↑