通过多模态与自监督结合，更准地发现商品的替代或互补关系。
Multi-modal Relational Item Representation Learning for Inferring Substitutable and Complementary Items
- 融合商品元数据与用户行为，用自监督去噪学习关系表示
- 在五个数据集上替代/互补预测准确率提升26.1%/39.2%
- 对冷启动商品也有效，适合电商推荐场景
我们研究替代品与互补品的推断问题，支撑替代购买与后续推荐等应用。现有方法通常基于行为构建的物品-物品关联（如共看、共购）使用图神经网络，或仅依赖物品内容。然而，这些方法常忽略两大挑战：(i) 用户行为（如共看、共购）仅提供噪声性强的弱监督信号；(ii) 行为信号呈长尾分布，导致许多物品关联稀疏。本文提出MMSC，一种自监督多模态关系表示学习框架，结合适配于物品元数据的多模态基础模型与自监督去噪模块，从噪声行为中学习关系感知表示，并通过分层聚合机制统一建模。进一步引入大语言模型辅助监督以缓解训练中行为信号的噪声。在五个真实世界数据集上的实验表明，MMSC在替代品与互补品推断任务上分别优于现有基线26.1%和39.2%，且对冷启动物品仍具有效性。代码已开源以供复现。
原文摘要 · Abstract (English)
We study the problem of inferring substitutable and complementary items, which underpins applications such as alternative and follow-up purchase suggestions. Existing approaches typically learn from behavior-derived item-item associations using GNNs or leverage item content alone. However, these methods often overlook two key challenges: (i) user behaviors (e.g., co-view/co-purchase) only provide noisy weak supervision, and (ii) behavior signals are long-tailed, leaving many items with sparse associations. We propose MMSC, a self-supervised multi-modal relational representation learning framework that combines a multi-modal foundation model adapted to encode item metadata and a self-supervised denoising module that learns relationship-aware representations from noisy user behaviors, unified by a hierarchical aggregation mechanism. We further use LLM-assisted supervision to mitigate noise in behavior-derived supervision during training. Experiments on five real-world datasets show that MMSC consistently outperforms existing baselines by 26.1% for substitutable and 39.2% for complementary item inference, while remaining effective for cold-start items. We share our code for reproducibility.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。