SDM uses multi-head self-attention over short-term sessions and a learned gate to fuse long-term preferences, reporting improved top-N recall and Taobao online metrics, but the headline comparison is not fully controlled.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2019 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
SDM: Sequential Deep Matching Model for Online Large-scale Recommender System
SDM uses multi-head self-attention over short-term sessions and a learned gate to fuse long-term preferences, reporting improved top-N recall and Taobao online metrics, but the headline comparison is not fully controlled.