URecJPQ: Memory-efficient Multimodal Recommendation Models through RecJPQ in Large-Scale Scenarios (opens in new tab)

Training state-of-the-art recommendation models on large-scale industrial datasets can be a challenging task due to the high number of users and items which are typically represented through ID embeddings. Such embeddings typically require a large amount of memory resources, which are not always available. This problem is further exacerbated in multimodal recommendation, in which multimodal item features generally improve recommendation performa...