arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.03221cs.IRcs.AIcs.LG
收藏

迈向轻量级跨域序列推荐:基于外部注意力增强的图卷积网络

Towards Lightweight Cross-domain Sequential Recommendation via External Attention-enhanced Graph Convolution Network

Shandong Normal University(山东师范大学)

Jinyu Zhang, Huichuan Duan, Lei Guo, Liancheng Xu, Xinhua Wang

AI总结:

针对跨域序列推荐中模型训练负担重和自注意力二次复杂度问题,提出轻量级框架LEA-GCN,通过单层聚合协议GCN编码器和双通道外部注意力组件,在不损失准确性的前提下显著降低模型体积与训练时间。

摘要:

跨域序列推荐(CSR)是一项新兴但具有挑战性的任务,它通过建模重叠用户在多个域中的交互来刻画其行为模式的演变。现有CSR研究主要集中于使用复合或深层结构,这些结构在准确性上取得了显著提升,但给模型训练带来了巨大负担。此外,为了学习用户特定的序列表示,现有工作通常采用全局相关性加权策略(如自注意力机制),其计算复杂度为二次方。在本工作中,我们引入了一个轻量级的、基于外部注意力增强的GCN框架来解决上述挑战,即LEA-GCN。具体而言,通过仅保留邻域聚合组件并使用单层聚合协议(SLAP),我们的轻量级GCN编码器能够更高效地捕获来自两个域的物品的协同过滤信号。为了进一步简化框架结构并聚合用户特定的序列模式,我们设计了一种新颖的双通道外部注意力(EA)组件,该组件通过轻量级线性结构计算所有物品之间的相关性。在两个真实世界数据集上进行了大量实验,结果表明,与几种最先进的方法相比,LEA-GCN在不影响准确性的情况下需要更小的模型体积和更少的训练时间。

英文摘要:

Cross-domain Sequential Recommendation (CSR) is an emerging yet challenging task that depicts the evolution of behavior patterns for overlapped users by modeling their interactions from multiple domains. Existing studies on CSR mainly focus on using composite or in-depth structures that achieve significant improvement in accuracy but bring a huge burden to the model training. Moreover, to learn the user-specific sequence representations, existing works usually adopt the global relevance weighting strategy (e.g., self-attention mechanism), which has quadratic computational complexity. In this work, we introduce a lightweight external attention-enhanced GCN-based framework to solve the above challenges, namely LEA-GCN. Specifically, by only keeping the neighborhood aggregation component and using the Single-Layer Aggregating Protocol (SLAP), our lightweight GCN encoder performs more efficiently to capture the collaborative filtering signals of the items from both domains. To further alleviate the framework structure and aggregate the user-specific sequential pattern, we devise a novel dual-channel External Attention (EA) component, which calculates the correlation among all items via a lightweight linear structure. Extensive experiments are conducted on two real-world datasets, demonstrating that LEA-GCN requires a smaller volume and less training time without affecting the accuracy compared with several state-of-the-art methods.

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。

↑