Research map / Label-efficient and robust learning / Recognition and long-tail
MM4Rec: Multi-Source and Multi-Scenario Recommender for Unified User Preference
Chu-Chun Yu, Ming-Yi Hong, Miao-Chen Chiang, Min Chen Hsieh, Che Lin
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 MSBE module (ablation) | MM4Rec · AviviD DatasetA Push Ads | NDCG@10: 0.461 -> 0.473 | Improved |
| add MSBE module (ablation) | MM4Rec · AviviD DatasetA Browse Ads | NDCG@10: 0.455 -> 0.469 | Improved |
| add MSBE module (ablation) | MM4Rec · AviviD DatasetA Browse News | HR@10: 0.701 -> 0.701 | No clear effect |
| add SATE to both temporal and contextual pathways (ablation) | MM4Rec · AviviD DatasetA Push Ads | NDCG@10: 0.461 -> 0.473 | Improved |
| add SATE to temporal pathway (ablation) | MM4Rec · AviviD DatasetA Push Ads | NDCG@10: 0.450 -> 0.473 | Improved |
| add SATE to contextual pathway (ablation) | MM4Rec · AviviD DatasetA Push Ads | NDCG@10: 0.459 -> 0.473 | Improved |
| add SATE to both pathways (ablation) | MM4Rec · AviviD DatasetA Browse Ads | HR@10: 0.735 vs 0.726 (w/o SATE in T&C) | Hurt |
| add SoAG dynamic source weighting instead of equal weights (ablation) | MM4Rec · AviviD DatasetA Push Ads | NDCG@10: 0.457 -> 0.473 | Improved |
| add source-specific FFNs instead of shared FFN (ablation) | MM4Rec · AviviD DatasetA Push Ads | NDCG@10: 0.451 -> 0.473 | Improved |
| add source-specific FFNs instead of shared FFN (ablation) | MM4Rec · AviviD DatasetA Browse Ads | NDCG@10: 0.446 -> 0.469 | Improved |
| use multi-scenario STAR-MM instead of STAR | STAR · AviviD DatasetA Browse Ads | NDCG@10: 0.468 -> 0.427 | Hurt |
| use MM4Rec instead of Push4Rec | Push4Rec · AviviD DatasetA Push Ads | NDCG@10: 0.425 -> 0.473 | Improved |
Closest papers by meaning
- CoT4Rec: Revealing User Preferences Through Chain of Thought for Recommender Systems (AAAI 2025 · similarity 0.85)
- Tree of Preferences for Diversified Recommendation (NeurIPS 2025 · similarity 0.85)
- Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations (ICML 2024 · similarity 0.85)
- Preference Diffusion for Recommendation (ICLR 2025 · similarity 0.85)
- Density-based User Representation using Gaussian Process Regression for Multi-interest Personalized Retrieval (NeurIPS 2024 · similarity 0.85)
- LLM4RSR: Large Language Models as Data Correctors for Robust Sequential Recommendation (AAAI 2025 · 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.
