Research map / Learning theory and algorithms / Fairness
Fairly Recommending with Social Attributes: A Flexible and Controllable Optimization Approach
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 accuracy constraint (ablation) | SoFA region 0 · KuaiRec SP/NSP | NDCG@5: 0.2181 -> 0.2349 | Helped |
| add accuracy constraint (ablation) | SoFA region 2 · KuaiRec SP/NSP | NDCG@5: 0.2117 -> 0.2329 | Helped |
| add accuracy constraint (ablation) | SoFA region 4 · KuaiRec SP/NSP | NDCG@5: 0.2193 -> 0.2402 | Helped |
| add accuracy constraint (ablation) | SoFA region 4 · Epinions SP/NSP | NDCG@5: 0.0169 -> 0.0185 | Helped |
| specify preference region (ablation) | SoFA · KuaiRec SP/NSP | NDCG@5: 0.2412 -> 0.2402 | No clear effect |
| remove SP fairness loss (ablation) | SoFA · KuaiRec SP/NSP | NDCG@5: 0.2220 | Mixed |
| relax accuracy threshold (1.1x, 1.2x, none) (ablation) | SoFA · KuaiRec SP/NSP | NDCG@5 | Hurt |
| lower accuracy threshold (ablation) | SoFA · KuaiRec SP/NSP | F1_SP | Helped |
| SoFA region 4 vs BPRMF | BPRMF · KuaiRec SP/NSP | F1_SP: 0.1037 -> 0.0077 | Helped |
| SoFA region 3 vs MOOMTL (add preference region and accuracy constraint) | MOOMTL · KuaiRec SP/NSP | NDCG@5: 0.2229 -> 0.2413 | Helped |
| SoFA region 4 vs SP Reg | + SP Reg · KuaiRec SP/NSP | F1_SP: 0.0091 -> 0.0077 | Helped |
| SoFA region 4 vs BPRMF | BPRMF · Epinions SP/NSP | NDCG@5: 0.0443 -> 0.0185 | Hurt |
Closest papers by meaning
- User-item fairness tradeoffs in recommendations (NeurIPS 2024 · similarity 0.89)
- Interpolating Item and User Fairness in Multi-Sided Recommendations (NeurIPS 2024 · similarity 0.88)
- Intra- and Inter-group Optimal Transport for User-Oriented Fairness in Recommender Systems (AAAI 2024 · similarity 0.86)
- Optimizing Social Network Interventions via Hypergradient-Based Recommender System Design (ICML 2025 · similarity 0.86)
- Disentangled Modeling of Preferences and Social Influence for Group Recommendation (AAAI 2025 · similarity 0.86)
- CUGF: A Reliable and Fair Recommendation Framework (AAAI 2025 · similarity 0.86)
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.