Research map / Optimization / Distributed and compressed
Incentivizing Honesty among Competitors in Collaborative Learning and Optimization
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 penalty weight C to rewards (peer-prediction-style penalty) (ablation) | FedSGD with noisy clients · FeMNIST | reward at high noise alphaA | Helped |
| Add penalty weight C to rewards (ablation) | FedSGD with noisy clients · Twitter | reward at high noise alphaA | Helped |
| Honest players pay penalties (C=0.0002) | Penalty mechanism · FeMNIST | penalty paid by honest players: less than 0.0031 | No clear effect |
| Use Twitter instead of FeMNIST (larger noise effect on loss) | Penalty mechanism · Twitter vs FeMNIST | loss degradation from noise: 0.084 vs 0.034 | Hurt |
| Replace Mean-based with Median-based aggregation (ablation) | SGD baseline · FeMNIST | effect of added noise on loss | Mixed |
| Apply penalty mechanism with Median-based aggregation (ablation) | Penalty mechanism · FeMNIST | reward vs noise | Helped |
| Large noise alphaA > 6 without projection step | FedSGD · FeMNIST | numerical stability | Hurt |
Closest papers by meaning
- Incentivized Truthful Communication for Federated Bandits (ICLR 2024 · similarity 0.87)
- Collaborative Mean Estimation Among Heterogeneous Strategic Agents: Individual Rationality, Fairness, and Truthful Contribution (ICML 2025 · similarity 0.87)
- Paid with Models: Optimal Contract Design for Collaborative Machine Learning (AAAI 2025 · similarity 0.87)
- Carrot and Stick: Eliciting Comparison Data and Beyond (NeurIPS 2024 · similarity 0.87)
- Training Generalizable Collaborative Agents via Strategic Risk Aversion (NeurIPS 2026 · similarity 0.86)
- A Cramér–von Mises Approach to Incentivizing Truthful Data Sharing (NeurIPS 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.