Fast Private Adaptive Query Answering for Large Data Domains

2026-02-05

AI Summary

This work addresses the high computational cost of the reconstruction phase in adaptive marginal query answering under differential privacy, particularly over large data domains. The authors propose a novel framework based on multidimensional arrays that integrates residual queries with a lazy update mechanism and an adaptive per-round privacy budget allocation strategy. By synergistically combining the strengths of AIM and GReM, the method significantly reduces computational complexity while maintaining controlled error bounds. Compared to the original AIM algorithm, the proposed approach achieves speedups of several orders of magnitude without sacrificing accuracy, thereby substantially improving both scalability and query precision in differentially private data analysis.

Technology Category

• Machine Learning: Privacy
• Data Mining & Knowledge Management: Intelligent Query Processing
• Search and Optimization: Distributed Search

Application Category

• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Privately releasing marginals of a tabular dataset is a foundational problem in differential privacy. However, state-of-the-art mechanisms suffer from a computational bottleneck when marginal estimates are reconstructed from noisy measurements. Recently, residual queries were introduced and shown to lead to highly efficient reconstruction in the batch query answering setting. We introduce new techniques to integrate residual queries into state-of-the-art adaptive mechanisms such as AIM. Our contributions include a novel conceptual framework for residual queries using multi-dimensional arrays, lazy updating strategies, and adaptive optimization of the per-round privacy budget allocation. Together these contributions reduce error, improve speed, and simplify residual query operations. We integrate these innovations into a new mechanism (AIM+GReM), which improves AIM by using fast residual-based reconstruction instead of a graphical model approach. Our mechanism is orders of magnitude faster than the original framework and demonstrates competitive error and greatly improved scalability.

Problem

• differential privacy
• marginal release
• adaptive query answering
• large data domains
• private data analysis

Innovation

• residual queries
• differential privacy
• adaptive mechanisms
• privacy budget allocation
• efficient reconstruction