2 papers
cs.LG2018
Ranking Distillation: Learning Compact Ranking Models With High Performance for Recommender System
Jiaxi Tang, Ke Wang
We propose a novel way to train ranking models, such as recommender systems, that are both effective and efficient. Knowledge distillation (KD) was shown to be successful in image…
cs.IR2018
Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding
Jiaxi Tang, Ke Wang
Top- sequential recommendation models each user as a sequence of items interacted in the past and aims to predict top- ranked items that a user will likely interact in a `nea…