作者位次 #2/9SIGIR 2026Oral· Information Retrieval (Full)
Well Begun is Half Done: Training-Free and Model-Agnostic Semantically Guaranteed User Representation Initialization for Multimodal Recommendation
Jinfeng Xu · Zheyu Chen · Shuo Yang · Jinze Li · Hewei Wang · Jianheng Tang · Wei Wang · Xiping Hu · Edith Cheuk-Han Ngai
摘要
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 initializ...