CDTM uses dual embeddings plus a learned transfer matrix and attention to improve click-through prediction in a target domain by transferring from multiple heterogeneous source domains, with reported offline AUC and online CTR/eCPM gains on NetEase data.
Field-aware factorization machines for ctr prediction,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Centralized-Distributed Transfer Model for Cross-Domain Recommendation Based on Multi-Source Heterogeneous Transfer Learning
CDTM uses dual embeddings plus a learned transfer matrix and attention to improve click-through prediction in a target domain by transferring from multiple heterogeneous source domains, with reported offline AUC and online CTR/eCPM gains on NetEase data.