Research map / Learning theory and algorithms / Fairness
Fair Representation Learning for Recommendation: A Mutual Information Perspective
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 |
|---|---|---|---|
| apply FairMI to BPR | BPR · MovieLens-1M, Top-10 | NDCG@10: 0.1943 -> 0.2022 | Helped |
| apply FairMI to BPR | BPR · MovieLens-1M, Top-10 | DP@10: 0.2854 -> 0.1381 | Helped |
| apply FairMI to GCN | GCN · MovieLens-1M, Top-10 | NDCG@10: 0.2025 -> 0.2128 | Helped |
| apply FairMI to GCN | GCN · MovieLens-1M, Top-10 | DP@10: 0.2937 -> 0.1337 | Helped |
| apply FairMI to BPR | BPR · Lastfm-360K, Top-10 | NDCG@10: 0.1959 -> 0.1932 | Hurt |
| apply FairMI to BPR | BPR · Lastfm-360K, Top-10 | DP@10: 0.2664 -> 0.1318 | Helped |
| apply FairMI to GCN | GCN · Lastfm-360K, Top-10 | NDCG@10: 0.1971 -> 0.1976 | Helped |
| apply FairMI to GCN | GCN · Lastfm-360K, Top-10 | DP@10: 0.2860 -> 0.1312 | Helped |
| use conditional MI instead of unconditional MI for retaining interaction information | FairMI · MovieLens-1M, Top-10 | DP@10: 0.1501 -> 0.1381 | Helped |
| use conditional MI instead of unconditional MI for retaining interaction information | FairMI · Lastfm-360K, Top-10 | DP@10: 0.1480 -> 0.1318 | Helped |
| add the MI lower bound for preserving interaction information (ablation) | FairMI with BPR · MovieLens-1M, Top-10 | NDCG: 0.1887 -> 0.2022 | Helped |
| add the MI lower bound for preserving interaction information (ablation) | FairMI with BPR · MovieLens-1M, Top-10 | DP: 0.1588 -> 0.1381 | Helped |
Closest papers by meaning
- User-item fairness tradeoffs in recommendations (NeurIPS 2024 · similarity 0.88)
- 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 0.87)
- No Prejudice! Fair Federated Graph Neural Networks for Personalized Recommendation (AAAI 2024 · similarity 0.87)
- CUGF: A Reliable and Fair Recommendation Framework (AAAI 2025 · similarity 0.86)
- ENSUR: Equitable and Statistically Unbiased Recommendation (ICML 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.