A Differentially Private Clustering Algorithm for Well-Clustered Graphs

• URL: http://arxiv.org/abs/2403.14332v1
• Date: Thu, 21 Mar 2024 11:57:16 GMT
• Title: A Differentially Private Clustering Algorithm for Well-Clustered Graphs
• Authors: Weiqiang He, Hendrik Fichtenberger, Pan Peng,
• Abstract summary: We provide an efficient ($epsilon,$delta$)-DP algorithm tailored specifically for such graphs. Our algorithm works for well-clustered graphs with $k$ nearly-balanced clusters.
• Score: 6.523602840064548
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study differentially private (DP) algorithms for recovering clusters in well-clustered graphs, which are graphs whose vertex set can be partitioned into a small number of sets, each inducing a subgraph of high inner conductance and small outer conductance. Such graphs have widespread application as a benchmark in the theoretical analysis of spectral clustering. We provide an efficient ($\epsilon$,$\delta$)-DP algorithm tailored specifically for such graphs. Our algorithm draws inspiration from the recent work of Chen et al., who developed DP algorithms for recovery of stochastic block models in cases where the graph comprises exactly two nearly-balanced clusters. Our algorithm works for well-clustered graphs with $k$ nearly-balanced clusters, and the misclassification ratio almost matches the one of the best-known non-private algorithms. We conduct experimental evaluations on datasets with known ground truth clusters to substantiate the prowess of our algorithm. We also show that any (pure) $\epsilon$-DP algorithm would result in substantial error.

Related papers

• A Mirror Descent-Based Algorithm for Corruption-Tolerant Distributed Gradient Descent [57.64826450787237]
  We show how to analyze the behavior of distributed gradient descent algorithms in the presence of adversarial corruptions. We show how to use ideas from (lazy) mirror descent to design a corruption-tolerant distributed optimization algorithm. Experiments based on linear regression, support vector classification, and softmax classification on the MNIST dataset corroborate our theoretical findings.
  arXiv  Detail & Related papers  (2024-07-19T08:29:12Z)
• Combinatorial Approximations for Cluster Deletion: Simpler, Faster, and Better [18.121514220195607]
  Cluster deletion is an NP-hard graph clustering objective with applications in computational and social network analysis. We first provide a tighter analysis of two previous approximation algorithms, improving their approximation guarantees from 4 to 3. We show that both algorithms can be derandomized in a surprisingly simple way, by greedily taking a maximum degree in an auxiliary graph and forming a cluster around it.
  arXiv  Detail & Related papers  (2024-04-24T18:39:18Z)
• Fast and Simple Spectral Clustering in Theory and Practice [7.070726553564701]
  Spectral clustering is a popular and effective algorithm designed to find $k$ clusters in a graph $G$. We present a simple spectral clustering algorithm based on a vertices embedding with $O(log(k))$ computed by the power method. We evaluate the new algorithm on several synthetic and real-world datasets, finding that it is significantly faster than alternative clustering algorithms, while producing results with approximately the same clustering accuracy.
  arXiv  Detail & Related papers  (2023-10-17T02:31:57Z)
• Latent Random Steps as Relaxations of Max-Cut, Min-Cut, and More [30.919536115917726]
  We present a probabilistic model based on non-negative matrix factorization which unifies clustering and simplification. By relaxing the hard clustering to a soft clustering, our algorithm relaxes potentially hard clustering problems to a tractable ones.
  arXiv  Detail & Related papers  (2023-08-12T02:47:57Z)
• One-step Bipartite Graph Cut: A Normalized Formulation and Its Application to Scalable Subspace Clustering [56.81492360414741]
  We show how to enforce a one-step normalized cut for bipartite graphs, especially with linear-time complexity. In this paper, we first characterize a novel one-step bipartite graph cut criterion with normalized constraints, and theoretically prove its equivalence to a trace problem. We extend this cut criterion to a scalable subspace clustering approach, where adaptive anchor learning, bipartite graph learning, and one-step normalized bipartite graph partitioning are simultaneously modeled.
  arXiv  Detail & Related papers  (2023-05-12T11:27:20Z)
• Differentially-Private Hierarchical Clustering with Provable Approximation Guarantees [79.59010418610625]
  We study differentially private approximation algorithms for hierarchical clustering. We show strong lower bounds for the problem: that any $epsilon$-DP algorithm must exhibit $O(|V|2/ epsilon)$-additive error for an input dataset. We propose a private $1+o(1)$ approximation algorithm which also recovers the blocks exactly.
  arXiv  Detail & Related papers  (2023-01-31T19:14:30Z)
• Hierarchical Clustering: $O(1)$-Approximation for Well-Clustered Graphs [3.2901541059183432]
  We present two-time approximation algorithms for hierarchical clustering. The significance of our work is demonstrated by the empirical analysis on both synthetic and real-world data sets.
  arXiv  Detail & Related papers  (2021-12-16T17:52:04Z)
• Solving correlation clustering with QAOA and a Rydberg qudit system: a full-stack approach [94.37521840642141]
  We study the correlation clustering problem using the quantum approximate optimization algorithm (QAOA) and qudits. Specifically, we consider a neutral atom quantum computer and propose a full stack approach for correlation clustering. We show the qudit implementation is superior to the qubit encoding as quantified by the gate count.
  arXiv  Detail & Related papers  (2021-06-22T11:07:38Z)
• Differentially Private Clustering: Tight Approximation Ratios [57.89473217052714]
  We give efficient differentially private algorithms for basic clustering problems. Our results imply an improved algorithm for the Sample and Aggregate privacy framework. One of the tools used in our 1-Cluster algorithm can be employed to get a faster quantum algorithm for ClosestPair in a moderate number of dimensions.
  arXiv  Detail & Related papers  (2020-08-18T16:22:06Z)
• Online Dense Subgraph Discovery via Blurred-Graph Feedback [87.9850024070244]
  We introduce a novel learning problem for dense subgraph discovery. We first propose a edge-time algorithm that obtains a nearly-optimal solution with high probability. We then design a more scalable algorithm with a theoretical guarantee.
  arXiv  Detail & Related papers  (2020-06-24T11:37:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.