Research map / Label-efficient and robust learning / Domain adaptation and generalization
Cross-Domain Adaptative Learning for Online Advertisement Customer Lifetime Value Prediction
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Apply cross-domain adaptive learning to the Mixed Model instead of training on target data alone | Mixed Model · G1–G5 | AUC: 0.680 -> 0.740; 0.667 -> 0.715; 0.723 -> 0.754; 0.736 -> 0.795; 0.653 -> 0.733 | Helped |
| Apply cross-domain adaptive learning to the Mixed Model instead of training on target data alone | Mixed Model · G1–G5 | normalized Gini: 0.536 -> 0.625; 0.545 -> 0.640; 0.539 -> 0.639; 0.546 -> 0.689; 0.396 -> 0.461 | Helped |
| Use CDAF rather than fine-tuning the source-pretrained model | Mixed Model · G1–G5 | AUC: 0.717 -> 0.740; 0.709 -> 0.715; 0.696 -> 0.755; 0.740 -> 0.795; 0.706 -> 0.734 | Helped |
| Add Wasserstein discrepancy minimization (ablation) | CDAF (Mixed Model) · G1 and G2 | AUC: 0.726 -> 0.740; 0.714 -> 0.715 | Mixed |
| Add Wasserstein discrepancy minimization (ablation) | CDAF (Mixed Model) · G1 and G2 | normalized Gini: 0.610 -> 0.625; 0.622 -> 0.640 | Helped |
| Add dual predictors' ℓ1 distance minimization (ablation) | CDAF (Mixed Model) · G1 and G2 | AUC: 0.734 -> 0.740; 0.709 -> 0.715 | Mixed |
| Add dual predictors' ℓ1 distance minimization (ablation) | CDAF (Mixed Model) · G1 and G2 | normalized Gini: 0.615 -> 0.625; 0.629 -> 0.640 | Mixed |
| Add source predictor supervised loss (ablation) | CDAF (Mixed Model) · G1 and G2 | AUC: 0.731 -> 0.740; 0.704 -> 0.715 | Helped |
| Add source predictor supervised loss (ablation) | CDAF (Mixed Model) · G1 and G2 | normalized Gini: 0.590 -> 0.625; 0.580 -> 0.640 | Helped |
| Add target predictor supervised loss (ablation) | CDAF (Mixed Model) · G1 and G2 | AUC: 0.717 -> 0.740; 0.710 -> 0.715 | Helped |
| Add target predictor supervised loss (ablation) | CDAF (Mixed Model) · G1 and G2 | normalized Gini: 0.593 -> 0.625; 0.640 -> 0.640 | Mixed |
Closest papers by meaning
- Invariant Deep Uplift Modeling for Incentive Assignment in Online Marketing via Probability of Necessity and Sufficiency (ICML 2025 · similarity 0.83)
- Towards Unbiased Information Extraction and Adaptation in Cross-Domain Recommendation (AAAI 2025 · similarity 0.82)
- LLM-Auction: Generative Auction towards LLM-Native Advertising (NeurIPS 2026 · similarity 0.82)
- Transfer Learning for Nonparametric Contextual Dynamic Pricing (ICML 2025 · similarity 0.82)
- Online Conversion Rate Prediction via Multi-Interval Screening and Synthesizing under Delayed Feedback (AAAI 2024 · similarity 0.82)
- Learning Personalized Ad Impact via Contextual Reinforcement Learning under Delayed Rewards (NeurIPS 2025 · similarity 0.81)
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.