Research map / Federated learning and privacy / Privacy attacks and secure learning
PPGenCDR: A Stable and Robust Framework for Privacy-Preserving Cross-Domain Recommendation
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 |
|---|---|---|---|
| Use PPGenCDR instead of PriCDR | PPCDR · Douban book → music | HR@5: .3074 -> .3701 | Helped |
| Use PPGenCDR instead of PriCDR | PPCDR · Amazon music → book | HR@5: .5605 -> .6012 | Helped |
| Use PPGenCDR instead of PriCDR | PPCDR · Douban movie → book | HR@5: .3577 -> .4238 | Helped |
| Use PPGenCDR instead of PriCDR | PPCDR · Amazon movie → book | HR@5: .5862 -> .6253 | Helped |
| Use PPGenCDR instead of PriCDR | PPCDR · Douban movie → music | HR@5: .3346 -> .3782 | Helped |
| Use PPGenCDR instead of PriCDR | PPCDR · Amazon movie → music | HR@5: .6015 -> .6379 | Helped |
| Add GAN stabilizer (ablation) | PPGenCDR · Douban book → music | HR@5: .2944 -> .3701 | Helped |
| Add GAN stabilizer (ablation) | PPGenCDR · Amazon music → book | HR@5: .5701 -> .6012 | Helped |
| Add GAN stabilizer (ablation) | PPGenCDR · Douban movie → book | HR@5: .3647 -> .4238 | Helped |
| Add robustness conductor (ablation) | PPGenCDR · Amazon movie → book | HR@5: .3614 -> .6253 | Helped |
| Add robustness conductor (ablation) | PPGenCDR · Douban movie → music | HR@5: .2739 -> .3782 | Helped |
| Apply RDP selectively to the discriminator gradients rather than the whole model (ablation) | PPGenCDR · Amazon movie source | HR: .1098 -> .0945 | Hurt |
Closest papers by meaning
- Reducing Item Discrepancy via Differentially Private Robust Embedding Alignment for Privacy-Preserving Cross Domain Recommendation (ICML 2024 · similarity 0.91)
- Federated Graph Learning for Cross-Domain Recommendation (NeurIPS 2024 · similarity 0.85)
- RRL: Recommendation Reverse Learning (AAAI 2024 · similarity 0.84)
- RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models (ICLR 2025 · similarity 0.83)
- Domain-Level Disentanglement Framework Based on Information Enhancement for Cross-Domain Cold-Start Recommendation (AAAI 2025 · similarity 0.83)
- Graph Disentangled Contrastive Learning with Personalized Transfer for Cross-Domain Recommendation (AAAI 2024 · similarity 0.83)
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.