无需用户隐私信息，也能高效实现数据删除的定价机制。
The Price of Ignorance: Information-Free Quotation for Data Retention in Machine Unlearning
- 设计无需用户隐私参数的逐步加价机制，由用户自主选择是否保留数据。
- 实测显示该机制福利损失不足1%，接近最优个性化定价效果。
- 适合关注合规性与公平性的数据删除系统设计者使用。
根据《通用数据保护条例》（GDPR）等法规，用户行使数据删除权时，运营商面临两难：过度机器遗忘会降低模型精度并增加重训练成本；而现有数据保留定价机制需知晓每位用户的隐私与准确率偏好，这在法规下难以实现。我们提出一种信息无关的上升报价机制，服务器广播逐步提高的价格，用户自主选择数据供应，无需了解其参数。在完全信息下，协议存在唯一子博弈完美均衡，表现为单期销售。我们定义了‘无知代价’——即完全知情最优定价与本机制之间的福利差距，并证明其效率存在三阶段排序。在七种机制、5000次蒙特卡洛模拟中，该机制福利达基准的≥99%，且具备抗噪声鲁棒性和良好公平性。
原文摘要 · Abstract (English)
When users exercise data deletion rights under the General Data Protection Regulation (GDPR) and similar regulations, mobile network operators face a tradeoff: excessive machine unlearning degrades model accuracy and incurs retraining costs, yet existing pricing mechanisms for data retention require the server to know every user's private privacy and accuracy preferences, which is infeasible under the very regulations that motivate unlearning. We ask: what is the welfare cost of operating without this private information? We design an information-free ascending quotation mechanism where the server broadcasts progressively higher prices and users self-select their data supply, requiring no knowledge of users' parameters. Under complete information, the protocol admits a unique subgame-perfect Nash equilibrium characterized by single-period selling. We formalize the Price of Ignorance -- the welfare gap between optimal personalized pricing (which knows everything) and our information-free quotation (which knows nothing) -- and prove a three-regime efficiency ordering. Numerical evaluation across seven mechanisms and 5000 Monte Carlo runs shows that this price is near zero: the information-free mechanism achieves >=99% of the welfare of its information-intensive benchmarks, while providing noise-robust guarantees and comparable fairness.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。