CIRP: Cross-Item Relational Pre-training for Multimodal Product Bundling

Yunshan Ma, Yingzhi He, WENJUN ZHONG, Xiang Wang, Roger Zimmermann, Tat-Seng Chua

Abstract: Product bundling has been a prevailing marketing strategy that is beneficial in the online shopping scenario. Effective product bundling methods depend on high-quality item representations capturing both the individual items' semantics and cross-item relations. However, previous item representation learning methods, either feature fusion or graph learning, suffer from inadequate cross-modal alignment and struggle to capture the cross-item relations for cold-start items. Multimodal pre-train models could be the potential solutions given their promising performance on various multimodal downstream tasks. However, the cross-item relations have been under-explored in the current multimodal pre-train models. To bridge this gap, we propose a novel and simple framework Cross-Item Relational Pre-training (CIRP) for item representation learning in product bundling. Specifically, we employ a multimodal encoder to generate image and text representations. Then we leverage both the cross-item contrastive loss (CIC) and individual item's image-text contrastive loss (ITC) as the pre-train objectives. Our method seeks to integrate cross-item relation modeling capability into the multimodal encoder. Therefore, even for cold-start items that have no relations, their representations are still relation-aware. Furthermore, to eliminate the potential noise and reduce the computational cost, we harness a relation pruning module to remove the noisy and redundant relations. We apply the item representations extracted by CIRP to the product bundling model ItemKNN, and experiments on three e-commerce datasets demonstrate that CIRP outperforms various leading representation learning methods.

Primary Subject Area: [Engagement] Multimedia Search and Recommendation

Secondary Subject Area: [Generation] Multimedia Foundation Models

Relevance To Conference: This work proposes a novel multimodal pre-training method, which is of the first time to integrate the relational information into a BLIP backbone. Therefore, our multmodal pre-train model can capture the relations among items, which have not been touched by the salient multimodal pre-train models. We believe this work is not only applicable to bundle recommendation but also induce a new paradigm of relational pre-training for multimodal foundation models.

Submission Number: 3509