Research map / Learning theory and algorithms / Fairness
Online Certification of Preference-Based Fairness for Personalized Recommender Systems
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 |
|---|---|---|---|
| Replace unconstrained optimal policies with equal-user-utility policies | Recommendation policies · Last.fm | total utility: 1552 -> 1726 | Hurt |
| Replace unconstrained optimal policies with equal-user-utility policies | Recommendation policies · Last.fm | average envy: 0.10 -> 0 | Hurt |
| Replace unconstrained optimal policies with equal-user-utility policies | Recommendation policies · Last.fm | proportion 0.05-envious: 0.61 -> 0 | Hurt |
| Replace unconstrained optimal policies with equal-user-utility policies | Recommendation policies · MovieLens | total utility: 1671 -> 1761 | Hurt |
| Replace unconstrained optimal policies with equal-user-utility policies | Recommendation policies · MovieLens | average envy: 0.04 -> 0 | Hurt |
| Replace unconstrained optimal policies with equal-user-utility policies | Recommendation policies · MovieLens | proportion 0.05-envious: 0.13 -> 0 | Hurt |
| Increase the number of latent factors from a severely misspecified model toward sufficient capacity | Matrix-completion recommender · MovieLens and Last.fm | degree of envy | Mixed |
| Use a lower softmax inverse temperature | Softmax recommender · MovieLens and Last.fm | envy-freeness | Helped |
| Make conservative exploration less strict by increasing alpha | OCEF · Bandit experiments | audit duration | Mixed |
| Make conservative exploration less strict by increasing alpha | OCEF · Bandit experiments | audit cost | Mixed |
Closest papers by meaning
- Interpolating Item and User Fairness in Multi-Sided Recommendations (NeurIPS 2024 · similarity 0.86)
- User-item fairness tradeoffs in recommendations (NeurIPS 2024 · similarity 0.85)
- Intra- and Inter-group Optimal Transport for User-Oriented Fairness in Recommender Systems (AAAI 2024 · similarity 0.85)
- CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence (NeurIPS 2024 · similarity 0.84)
- CUGF: A Reliable and Fair Recommendation Framework (AAAI 2025 · similarity 0.84)
- Building Higher-Order Abstractions from the Components of Recommender Systems (AAAI 2024 · 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.