arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.17334cs.IRcs.AI
收藏

BiVRec:基于双向视图的多模态序列推荐

BiVRec: Bidirectional View-based Multimodal Sequential Recommendation

City University of Hong Kong(香港城市大学);Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Michigan State University(密歇根州立大学);Shanghai Jiaotong University(上海交通大学);Jinan University(暨南大学);The University of Queensland(昆士兰大学)

Jiaxi Hu, Jingtong Gao, Xiangyu Zhao, Yuehong Hu, Yuxuan Liang, Yiqi Wang, Ming He, Zitao Liu, Hongzhi Yin

AI总结:

针对多模态序列推荐两类范式的缺陷,提出BiVRec框架,通过多尺度兴趣嵌入、视图内兴趣分解、跨视图兴趣学习模块,联合ID与多模态视图双向提升推荐性能,在五个数据集达SOTA。

摘要:

近年来,将多模态信息融入序列推荐系统已成为研究热点。多模态序列推荐模型发展初期,主流范式是以ID为主导的推荐,即把多模态信息作为侧信息进行融合。然而,受限于可迁移性不足与信息侵入问题,另一种范式应运而生,该范式直接利用多模态特征进行推荐,可实现跨数据集推荐,但它忽略了用户ID信息,导致信息利用率低、训练成本高。为此,我们提出创新框架BiVRec,在ID视图与多模态视图下联合训练推荐任务,利用二者的协同关系双向提升推荐性能。为解决信息异构问题,我们首先构建结构化用户兴趣表示,再学习二者间的协同关系。具体而言,BiVRec包含三个模块:多尺度兴趣嵌入模块,通过多尺度分块扩展用户交互序列,全面建模用户兴趣;视图内兴趣分解模块,借助精心设计的高斯注意力与聚类注意力,构建高度结构化的兴趣表示;跨视图兴趣学习模块,通过粗粒度整体语义相似度与细粒度兴趣分配相似度,学习两种推荐视图间的协同关系。BiVRec在五个数据集上取得了当前最优性能,展现出多方面的实际优势。

英文摘要:

The integration of multimodal information into sequential recommender systems has attracted significant attention in recent research. In the initial stages of multimodal sequential recommendation models, the mainstream paradigm was ID-dominant recommendations, wherein multimodal information was fused as side information. However, due to their limitations in terms of transferability and information intrusion, another paradigm emerged, wherein multimodal features were employed directly for recommendation, enabling recommendation across datasets. Nonetheless, it overlooked user ID information, resulting in low information utilization and high training costs. To this end, we propose an innovative framework, BivRec, that jointly trains the recommendation tasks in both ID and multimodal views, leveraging their synergistic relationship to enhance recommendation performance bidirectionally. To tackle the information heterogeneity issue, we first construct structured user interest representations and then learn the synergistic relationship between them. Specifically, BivRec comprises three modules: Multi-scale Interest Embedding, comprehensively modeling user interests by expanding user interaction sequences with multi-scale patching; Intra-View Interest Decomposition, constructing highly structured interest representations using carefully designed Gaussian attention and Cluster attention; and Cross-View Interest Learning, learning the synergistic relationship between the two recommendation views through coarse-grained overall semantic similarity and fine-grained interest allocation similarity BiVRec achieves state-of-the-art performance on five datasets and showcases various practical advantages.

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。

↑