With the development of multimedia applications, multimodal recommendations are playing an essential role, as they can leverage rich contexts beyond user interactions. Existing methods mainly regard multimodal information as an auxiliary, using them to help learn ID features; however, there exist semantic gaps among multimodal content features and ID features, for which directly using multimodal information as an auxiliary would lead to misalignment in representations of users and items. In this paper, we first systematically investigate the misalignment issue in multimodal recommendations, and propose a solution named AlignRec. In AlignRec, the recommendation objective is decomposed into three alignments, namely alignment within contents, alignment between content and categorical ID, and alignment between users and items. Each alignment is characterized by a specific objective function and is integrated into our multimodal recommendation framework. To effectively train our AlignRec, we propose starting from pre-training the first alignment to obtain unified multimodal features and subsequently training the following two alignments together with these features as input. As it is essential to analyze whether each multimodal feature helps in training, we design three new classes of metrics to evaluate intermediate performance. Our extensive experiments on three real-world datasets consistently verify the superiority of AlignRec compared to nine baselines. We also find that the multimodal features generated by AlignRec are better than currently used ones, which are to be open-sourced.

翻译：随着多媒体应用的发展，多模态推荐因其能利用用户交互之外的丰富上下文信息而扮演着重要角色。现有方法主要将多模态信息视为辅助，用于帮助学习ID特征；然而，多模态内容特征与ID特征之间存在语义鸿沟，直接使用多模态信息作为辅助会导致用户和物品的表示出现错位。本文首先系统研究了多模态推荐中的错位问题，并提出名为AlignRec的解决方案。在AlignRec中，推荐目标被分解为三个对齐：内容内部对齐、内容与类别ID对齐、用户与物品对齐。每个对齐由特定目标函数表征，并集成到我们的多模态推荐框架中。为有效训练AlignRec，我们提出先预训练第一个对齐以获得统一多模态特征，随后将这些特征作为输入联合训练后两个对齐。鉴于分析每个多模态特征是否有助于训练至关重要，我们设计了三个新指标类别来评估中间性能。在三个真实数据集上的大量实验一致验证了AlignRec相对于九个基准模型的优越性。我们还发现AlignRec生成的多模态特征优于当前使用的特征，这些特征将开源。