Latent Structure Mining With Contrastive Modality Fusion for Multimedia Recommendation

Abstract

Multimedia contents are of predominance in the modern Web era. Recent years have witnessed growing research interests in multimedia recommendation, which aims to predict whether a user will interact with an item with multimodal contents. Most previous studies focus on modeling user-item interactions with multimodal features included as side information. However, this scheme is not well-designed for multimedia recommendation. First, only <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">collaborative</i> item-item relationships are implicitly modeled through high-order item-user-item co-occurrences. Considering that items are associated with rich contents in multiple modalities, we argue that the latent <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">semantic</i> item-item structures underlying these multimodal contents could be beneficial for learning better item representations and assist the recommender models to comprehensively discover candidate items. Second, although previous studies consider multiple modalities, their ways of fusing multiple modalities by linear combination or concatenation is insufficient to fully capture content information of items and item relationships. To address these deficiencies, we propose a latent structure <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MI</u> ning with <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</u> ont <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</u> astive m <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</u> dality fusion model, which we term MICRO for brevity. To be specific, we devise a novel modality-aware structure learning module, which learns item-item relationships for each modality. Based on the learned modality-aware latent item relationships, we perform graph convolutions to explicitly inject item affinities into modality-aware item representations. Additionally, we design a novel multimodal contrastive framework to facilitate item-level multimodal fusion by mining both modality-shared and modality-specific information. Finally, the item representations are plugged into existing collaborative filtering methods to make accurate recommendation. Extensive experiments on three real-world datasets demonstrate the superiority of our method over state-of-arts and rationalize the design choice of our work.