MA-DNN augments DNNs with per-user memory vectors capturing likes and dislikes to exploit historical behavior for CTR prediction while remaining simpler than RNNs.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.IR 2years
2019 2representative citing papers
Meta-path candidate retrieval plus adapted Attention-GRU ranking produces personalized queries for single-round interactive recommendation, deployed on Taobao with public code and data.
citing papers explorer
-
Click-Through Rate Prediction with the User Memory Network
MA-DNN augments DNNs with per-user memory vectors capturing likes and dislikes to exploit historical behavior for CTR prediction while remaining simpler than RNNs.
-
Query-based Interactive Recommendation by Meta-Path and Adapted Attention-GRU
Meta-path candidate retrieval plus adapted Attention-GRU ranking produces personalized queries for single-round interactive recommendation, deployed on Taobao with public code and data.