Research map / Label-efficient and robust learning / Recognition and long-tail
Deep Match to Rank Model for Personalized Click-Through Rate Prediction
Ze Lyu, Yu Dong, Chengfu Huo, Weijun Ren
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add auxiliary match network supervising User-to-Item Network (ablation) | DMR · Alimama public dataset | AUC: 0.6432 -> 0.6447 | Improved |
| add auxiliary match network (ablation) | DMR · Industrial dataset | AUC: 0.6905 -> 0.6921 | Improved |
| add positional encoding in User-to-Item Network (ablation) | DMR · Industrial dataset | AUC: 0.6890 -> 0.6921 | Improved |
| add positional encoding in User-to-Item Network (ablation) | DMR · Alimama public dataset | AUC: 0.6438 -> 0.6447 | Improved |
| add Item-to-Item Network to User-to-Item Network alone (ablation) | DMR · Industrial dataset | AUC: 0.6916 -> 0.6921 | Improved |
| add User-to-Item Network to Item-to-Item Network alone (ablation) | DMR · Alimama public dataset | AUC: 0.6424 -> 0.6447 | Improved |
| use separate item embedding matrix instead of doubled shared embedding (ablation) | DMR · Alimama public dataset | AUC: 0.6439 -> 0.6447 | Improved |
| replace DIEN with DMR | DIEN · Alimama public dataset | AUC: 0.6420 -> 0.6447 | Improved |
| replace DIN with DMR in online A/B test | DIN · Alibaba online A/B | CTR: +5.5% | Improved |
Closest papers by meaning
- AT4CTR: Auxiliary Match Tasks for Enhancing Click-Through Rate Prediction (AAAI 2024 · similarity 0.91)
- From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models (ICML 2025 · similarity 0.89)
- Addressing Cold-Start Problem in Click-Through Rate Prediction via Supervised Diffusion Modeling (AAAI 2025 · similarity 0.87)
- Preference Diffusion for Recommendation (ICLR 2025 · similarity 0.86)
- UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence (NeurIPS 2026 · similarity 0.85)
- On Softmax Direct Preference Optimization for Recommendation (NeurIPS 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
