Research map / Label-efficient and robust learning / Domain adaptation and generalization
Deeply Fusing Reviews and Contents for Cold Start Users in Cross-Domain Recommendation Systems
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 |
|---|---|---|---|
| add review text side information (R-DFM vs DFM) (ablation) | DFM · Movies & Books K=10 φ=80% | RMSE: 0.9987 -> 0.9893 | Helped |
| add item contents (RC-DFM vs R-DFM) (ablation) | R-DFM · Movies & Books K=10 φ=80% | RMSE: 0.9893 -> 0.9770 | Helped |
| add item contents (RC-DFM vs R-DFM) (ablation) | R-DFM · Movies & Music CDs K=10 φ=20% | MAE: 0.8360 -> 0.8005 | Helped |
| SDAE on rating vectors (DFM) instead of matrix factorization (EMCDR) (ablation) | EMCDR · Movies & Books K=10 φ=80% | RMSE: 1.5276 -> 0.9987 | Helped |
| SDAE on rating vectors (DFM) instead of matrix factorization (EMCDR) (ablation) | EMCDR · Movies & Music CDs K=30 φ=20% | MAE: 0.8190 -> 0.8328 | Hurt |
| RC-DFM vs EMCDR | EMCDR · Movies & Books K=10 φ=20% | RMSE: 1.0482 -> 0.9535 | Helped |
| use complete item plots (RC-DFM-Full) (ablation) | RC-DFM · Movies & Books | RMSE | Helped |
Closest papers by meaning
- Domain-Level Disentanglement Framework Based on Information Enhancement for Cross-Domain Cold-Start Recommendation (AAAI 2025 · similarity 0.92)
- Towards Unbiased Information Extraction and Adaptation in Cross-Domain Recommendation (AAAI 2025 · similarity 0.87)
- Graph Disentangled Contrastive Learning with Personalized Transfer for Cross-Domain Recommendation (AAAI 2024 · similarity 0.86)
- DisCo: Graph-Based Disentangled Contrastive Learning for Cold-Start Cross-Domain Recommendation (AAAI 2025 · similarity 0.86)
- Learning Accurate and Bidirectional Transformation via Dynamic Embedding Transportation for Cross-Domain Recommendation (AAAI 2024 · similarity 0.85)
- One for Dozens: Adaptive REcommendation for All Domains with Counterfactual Augmentation (AAAI 2025 · similarity 0.84)
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.