IISAN: Efficiently Adapting Multimodal Representation for Sequential Recommendation - M2.6

Explore a 14-minute conference talk from SIGIR 2024 focusing on IISAN, an innovative approach for efficiently adapting multimodal representation in sequential recommendation systems. Delve into the research presented by authors Junchen Fu, Xuri Ge, Xin Xin, Alexandros Karatzoglou, Ioannis Arapakis, Jie Wang, and Joemon Jose as they discuss the implementation of Decoupled PEFT (Parameter-Efficient Fine-Tuning) techniques. Gain insights into how this method enhances the performance and efficiency of multimodal recommender systems, potentially revolutionizing the field of sequential recommendations.

SIGIR 2024 M2.6 [fp] IISAN: Efficiently Adapting Multimodal Representation for Sequential Rec