Res-embedding combines central embeddings derived from user interest graphs with residual components to achieve better generalization in deep CTR prediction models, supported by a theoretical proof on embedding aggregation radius.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Res-embedding for Deep Learning Based Click-Through Rate Prediction Modeling
Res-embedding combines central embeddings derived from user interest graphs with residual components to achieve better generalization in deep CTR prediction models, supported by a theoretical proof on embedding aggregation radius.