Top-k frequent itemsets via differentially private FP-trees

By Jaewoo Lee, Chris Clifton. 2014

85 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Daniel Kifer
2. Ashwin Machanavajjhala
3. Ninghui Li
4. Philip S. Yu
5. Danfeng Zhang
6. Dong Su
7. Yan Chen
8. Guanhong Wang

In Information Systems

1. Philip S. Yu
2. Dong Su
3. Qian Xiao
4. Min Lyu
5. Ninghui Li
6. Wanlei Zhou
7. Daniel Kifer
8. Ahmed M Abdelhadi

Citations in the corpus

• Detecting Violations of Differential Privacy (2018, background): “(d) iSVT 3 [27] query noise does not scale with N .”
• Understanding the Sparse Vector Technique for Differential Privacy (2016, methodology): “In this paper, we limit our attention to SVT variants to those sa tisfying ǫ-DP, which are what have been used in the data mining community [1, 13, 17, 18].”
• Differential Privacy for Deep and Federated Learning: A Survey (2022, methodology): “…work can be divided into two categories: 1) The first category is the works producing pre-processing datasets balancing between accuracy and privacy for a specific learning model, such as frequent itemset mining models [71], [96], [97], and classi-fication and clustering models [53], [72], [98], [99].”
• Differentially Private Algorithms for Empirical Machine Learning (2014, background): “In particular it significantly outperforms NOISYCUT under small thresholds (or when many features must be chosen).”
• Differentially Private High-Dimensional Data Publication via Sampling-Based Inference (2015, methodology): “This framework is made possible by a generic threshold mechanism, which is an extended version of the sparse vector technique [10] and the threshold query technique [16].”
• On the Privacy Properties of Variants on the Sparse Vector Technique (2015, methodology): “Hence, generalized private threshold testing has been used to develop algorithms with high utility for private frequent itemset mining [6], feature selection in private classification [9] and generating synthetic data [2].”
• Differentially Private Data Publishing and Analysis: A Survey (2017, methodology): “[64] proposed an FP-tree based frequent itemset mining algorithm.”