Research map / Learning theory and algorithms / Fairness
Collaborative Machine Learning with Incentive-Aware Model Rewards
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 information gain on model parameters to value collaborative data | Collaborative model rewards · Friedman synthetic, DiaP, CaliH, BosH | MNLP | Mixed |
| Reduce ρ from 1 to 0.5 (ablation) | Incentive-aware model reward scheme · Friedman synthetic, DiaP, CaliH, BosH | MNLP | Helped |
| Reduce ρ from 1 to 0 (ablation) | Incentive-aware model reward scheme · Friedman synthetic | group welfare | Helped |
| Reduce ρ from 1 to 0.5 (ablation) | Incentive-aware model reward scheme · Friedman synthetic, DiaP, CaliH, BosH | MNLP: around 15% | Mixed |
Closest papers by meaning
- Paid with Models: Optimal Contract Design for Collaborative Machine Learning (AAAI 2025 · similarity 0.91)
- Incentivizing Time-Aware Fairness in Data Sharing (NeurIPS 2025 · similarity 0.90)
- Aequa: Fair Model Rewards in Collaborative Learning via Slimmable Networks (ICML 2025 · similarity 0.88)
- You Get What You Give: Reciprocally Fair Federated Learning (ICML 2025 · similarity 0.85)
- Learning the Expected Core of Strictly Convex Stochastic Cooperative Games (NeurIPS 2024 · similarity 0.84)
- Explaining Probabilistic Models with Distributional Values (ICML 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.