Graph-based Clustering under Differential Privacy
نویسندگان
چکیده
In this paper, we present the first differentially private clustering method for arbitrary-shaped node clusters in a graph. This algorithm takes as input only an approximate Minimum Spanning Tree (MST) T released under weight differential privacy constraints from the graph. Then, the underlying nonconvex clustering partition is successfully recovered from cutting optimal cuts on T . As opposed to existing methods, our algorithm is theoretically well-motivated. Experiments support our theoretical findings.
منابع مشابه
Privacy-Integrated Graph Clustering Through Differential Privacy
Data mining tasks like graph clustering can automatically process a large amount of data and retrieve valuable information. However, publishing such graph clustering results also involves privacy risks. In particular, linking the result with available background knowledge can disclose private information of the data set. The strong privacy guarantees of the differential privacy model allow copi...
متن کاملMinimum spanning tree release under differential privacy constraints
We investigate the problem of nodes clustering under privacy constraints when representing a dataset as a graph. Our contribution is threefold. First we formally define the concept of differential privacy for structured databases such as graphs, and give an alternative definition based on a new neighborhood notion between graphs. This definition is adapted to particular frameworks that can be m...
متن کاملDifferentially private subspace clustering
Subspace clustering is an unsupervised learning problem that aims at grouping data points into multiple “clusters” so that data points in a single cluster lie approximately on a low-dimensional linear subspace. It is originally motivated by 3D motion segmentation in computer vision, but has recently been generically applied to a wide range of statistical machine learning problems, which often i...
متن کاملBeyond Worst-Case Analysis in Privacy and Clustering: Exploiting Explicit and Implicit Assumptions
This thesis can be viewed as a collection of work in differential privacy and in clustering. In its first part we discuss work aimed at preserving differential privacy in a social network, with respect to either the presence/absence of a single edge [41], or with respect to changing all edges adjacent to one node [42]. In its second part we discuss multiple clustering problems, focusing on the ...
متن کاملPreserving Differential Privacy in Degree-Correlation based Graph Generation
Enabling accurate analysis of social network data while preserving differential privacy has been challenging since graph features such as cluster coefficient often have high sensitivity, which is different from traditional aggregate functions (e.g., count and sum) on tabular data. In this paper, we study the problem of enforcing edge differential privacy in graph generation. The idea is to enfo...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2018