Research map / Label-efficient and robust learning / Recognition and long-tail
Curriculum Disentangled Recommendation with Noisy Multi-feedback
Hong Chen, Yudong Chen, Xin Wang, Ruobing Xie, Rui Wang, Feng Xia, Wenwu Zhu
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 adjustable self-evaluating curriculum (ablation) | CDR · Amazon-Beauty | AUC: 0.7914 -> 0.7991 | Improved |
| add adjustable self-evaluating curriculum (ablation) | CDR · Amazon-Sports | AUC: 0.8083 -> 0.8152 | Improved |
| add adjustable self-evaluating curriculum (ablation) | CDR · MovieLens-1M | AUC: 0.8972 -> 0.9065 | Improved |
| add adjustable self-evaluating curriculum (ablation) | CDR · WeChat5D | AUC: 0.7548 -> 0.7622 | Improved |
| add raw unclick history without co-filtering (ablation) | CDR click-only · Amazon-Beauty | AUC: 0.7477 -> 0.7477 | No clear effect |
| add raw unclick history without co-filtering (ablation) | CDR click-only · Amazon-Sports | AUC: 0.8006 -> 0.7969 | Hurt |
| add raw unclick history without co-filtering (ablation) | CDR click-only · MovieLens-1M | AUC: 0.8879 -> 0.8854 | Hurt |
| add raw unclick history without co-filtering (ablation) | CDR click-only · WeChat5D | AUC: 0.7347 -> 0.7340 | Hurt |
| add co-filtering dynamic routing to click+unclick history (ablation) | CDR c&un · Amazon-Beauty | AUC: 0.7477 -> 0.7914 | Improved |
| add co-filtering dynamic routing to click+unclick history (ablation) | CDR c&un · WeChat5D | AUC: 0.7340 -> 0.7548 | Improved |
| set curriculum speed tau=1.0 (no decay) (ablation) | CDR curriculum · Amazon-Sports | AUC: 0.8152 -> 0.5645 | Hurt |
| curriculum difficulty thre=1.0 (focus on hardest samples) (ablation) | CDR curriculum · Amazon-Sports/Beauty | AUC | Hurt |
Closest papers by meaning
- Graph Disentangled Contrastive Learning with Personalized Transfer for Cross-Domain Recommendation (AAAI 2024 · similarity 0.88)
- DisCo: Graph-Based Disentangled Contrastive Learning for Cold-Start Cross-Domain Recommendation (AAAI 2025 · similarity 0.87)
- Disentangled Contrastive Bundle Recommendation with Conditional Diffusion (AAAI 2025 · similarity 0.86)
- Disentangled Modeling of Preferences and Social Influence for Group Recommendation (AAAI 2025 · similarity 0.85)
- Curriculum Conditioned Diffusion for Multimodal Recommendation (AAAI 2025 · similarity 0.84)
- Unbiased Recommender Learning from Implicit Feedback via Weakly Supervised Learning (ICML 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.
