Incentivizing Honesty among Competitors in Collaborative Learning and Optimization
cs.LG, cs.GT, stat.ML
Submitted: 2023-05-25
Updated: 2026-09-14
Comments: Corrected an error in Theorem 5.2: The previous statement omitted a necessary assumption on the strategy space. See Remark 5.3. Updated experimental results after fixing a mistake in the code. Previous version published in NeurIPS 2023; 37 pages, 5 figures
Code: https://github.com/TalwalkarLab/leaf
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Mitigating Bias in Federated Learning
- LEAF: A Benchmark for Federated Settings
- Linear Speedup in Personalized Collaborative Learning
- FL Games: A federated learning framework for distribution shifts
- Incentive Mechanisms for Federated Learning: From Economic and Game Theoretic Perspective
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks