Efficient noise-tolerant learning from statistical queries
Journal of the ACM (JACM)
Obtaining calibrated probability estimates from decision trees and naive Bayesian classifiers
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Learning and evaluating classifiers under sample selection bias
ICML '04 Proceedings of the twenty-first international conference on Machine learning
Practical privacy: the SuLQ framework
Proceedings of the twenty-fourth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems
Making generative classifiers robust to selection bias
Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining
A learning theory approach to non-interactive database privacy
STOC '08 Proceedings of the fortieth annual ACM symposium on Theory of computing
Sample Selection Bias Correction Theory
ALT '08 Proceedings of the 19th international conference on Algorithmic Learning Theory
Differential privacy: a survey of results
TAMC'08 Proceedings of the 5th international conference on Theory and applications of models of computation
Differential privacy based on importance weighting
Machine Learning
Hi-index | 0.00 |
This paper presents a fundamentally new approach to allowing learning algorithms to be applied to a dataset, while still keeping the records in the dataset confidential. Let D be the set of records to be kept private, and let E be a fixed set of records from a similar domain that is already public. The idea is to compute and publish a weight w(x) for each record x in E that measures how representative it is of the records in D. Data mining on E using these importance weights is then approximately equivalent to data mining directly on D. The dataset D is used by its owner to compute the weights, but not revealed in any other way.