Search papers, labs, and topics across Lattice.
The paper introduces Semantically Guaranteed User Representation Initialization (SG-URInit), a novel approach to initialize user embeddings in multimodal recommendation systems by leveraging item modality features and user cluster information. This addresses the semantic gap between randomly initialized user representations and semantically rich item representations. Experiments on real-world datasets demonstrate that SG-URInit significantly improves recommendation performance, alleviates the item cold-start problem, and accelerates model convergence when integrated into existing multimodal recommendation models.
Dramatically improve multimodal recommendation accuracy without any training by initializing user embeddings with item modality features and user cluster information.
Recent advancements in multimodal recommendations, which leverage diverse modality information to mitigate data sparsity and improve recommendation accuracy, have gained significant attention. However, existing multimodal recommendations overlook the critical role of user representation initialization. Unlike items, which are naturally associated with rich modality information, users lack such inherent information. Consequently, item representations initialized based on meaningful modality information and user representations initialized randomly exhibit a significant semantic gap. To this end, we propose a Semantically Guaranteed User Representation Initialization (SG-URInit). SG-URInit constructs the initial representation for each user by integrating both the modality features of the items they have interacted with and the global features of their corresponding clusters. SG-URInit enables the initialization of semantically enriched user representations that effectively capture both local (item-level) and global (cluster-level) semantics. Our SG-URInit is training-free and model-agnostic, meaning it can be seamlessly integrated into existing multimodal recommendation models without incurring any additional computational overhead during training. Extensive experiments on multiple real-world datasets demonstrate that incorporating SG-URInit into advanced multimodal recommendation models significantly enhances recommendation performance. Furthermore, the results show that SG-URInit can further alleviate the item cold-start problem and also accelerate model convergence, making it an efficient and practical solution for multimodal recommendations.
CMU ML