Strategyproof Learning: Building Trustworthy User-Generated Datasets
arXiv:2106.02398
Abstract
We prove in this paper that, perhaps surprisingly, incentivizing data misreporting is not a fatality. By leveraging a careful design of the loss function, we propose Licchavi, a global and personalized learning framework with provable strategyproofness guarantees. Essentially, we prove that no user can gain much by replying to Licchavi's queries with answers that deviate from their true preferences. Interestingly, Licchavi also promotes the desirable "one person, one unit-force vote" fairness principle. Furthermore, our empirical evaluation of its performance showcases Licchavi's real-world applicability. We believe that our results are critical for the safety of any learning scheme that leverages user-generated data.
31 pages
References in corpus (6)
- Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
- The Radicalization Risks of GPT-3 and Advanced Neural Language Models
- Lower Bounds and Optimal Algorithms for Personalized Federated Learning
- Examining Autocompletion as a Basic Concept for Interaction with Generative AI
- Tournesol: A quest for a large, secure and trustworthy database of reliable human judgments
- On the Strategyproofness of the Geometric Median