Research map / Label-efficient and robust learning / Domain adaptation and generalization
Dual-Perspective Disentanglement: Learning Symmetric Group-Aware Representations for Cross-Domain Recommendation
Borui Wu, Yuanbo Xu
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 |
|---|---|---|---|
| replace DisenCDR with DPGCDR | CDR model · Elec (Elec&Cloth) | HR@10: 24.88 -> 29.21 | Improved |
| replace DisenCDR with DPGCDR | CDR model · Elec (Elec&Cloth) | NDCG@10: 14.60 -> 18.27 | Improved |
| replace DisenCDR with DPGCDR | CDR model · Phone (Sport&Phone) | HR@10: 22.03 -> 27.46 | Improved |
| replace DisenCDR with DPGCDR | CDR model · Cloth (Elec&Cloth) | HR@10: 15.14 -> 13.63 | Hurt |
| replace DisenCDR with DPGCDR | CDR model · Cloth (Sport&Cloth) | HR@10: 15.70 -> 13.65 | Hurt |
| replace DisenCDR with DPGCDR | CDR model · Elec (Elec&Phone) | HR@10: 23.20 -> 23.26 | No clear effect |
| add dynamic grouping stage after warm-up (ablation) | DPGCDR · Elec (Elec&Cloth) | HR@10: 24.56 -> 29.21 | Improved |
| add dynamic grouping stage after warm-up (ablation) | DPGCDR · Cloth (Elec&Cloth) | HR@10: 10.43 -> 13.63 | Improved |
| add dynamic grouping stage after warm-up (ablation) | DPGCDR · Sport (Sport&Phone) | HR@10: 15.49 -> 18.74 | Improved |
| add dynamic grouping to the weakest (cold-start) user group (ablation) | DPGCDR · Sport&Phone user groups | HR@10 | Improved |
| add user-side branch to item-only disentanglement (both sides) (ablation) | DPGCDR · Phone->Elec | HR@10 | Improved |
| add item perspective to user-only model (ablation) | DPGCDR · Cloth->Elec | HR@10 | Improved |
Closest papers by meaning
- Graph Disentangled Contrastive Learning with Personalized Transfer for Cross-Domain Recommendation (AAAI 2024 · similarity 0.90)
- DisCo: Graph-Based Disentangled Contrastive Learning for Cold-Start Cross-Domain Recommendation (AAAI 2025 · similarity 0.90)
- Disentangled Modeling of Preferences and Social Influence for Group Recommendation (AAAI 2025 · similarity 0.88)
- Learning Accurate and Bidirectional Transformation via Dynamic Embedding Transportation for Cross-Domain Recommendation (AAAI 2024 · similarity 0.88)
- Domain-Level Disentanglement Framework Based on Information Enhancement for Cross-Domain Cold-Start Recommendation (AAAI 2025 · similarity 0.88)
- Learning Multiple User Distributions for Recommendation via Guided Conditional Diffusion (AAAI 2025 · similarity 0.87)
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.
