Near-Optimal Correlation Clustering with Privacy

@article{CohenAddad2022NearOptimalCC,
  title={Near-Optimal Correlation Clustering with Privacy},
  author={Vincent Cohen-Addad and Chenglin Fan and Silvio Lattanzi and Slobodan Mitrovi'c and Ashkan Norouzi-Fard and Nikos Parotsidis and Jakub Tarnawski},
  journal={ArXiv},
  year={2022},
  volume={abs/2203.01440}
}
Correlation clustering is a central problem in unsupervised learning, with applications spanning community detection, duplicate detection, automated labelling and many more. In the correlation clustering problem one receives as input a set of nodes and for each node a list of co-clustering preferences, and the goal is to output a clustering that minimizes the disagreement with the specified nodes’ preferences. In this paper, we introduce a simple and computationally efficient algorithm for the… 
View PDF on arXiv
2 Citations
Highly Influential Citations
1
Background Citations
1

2 Citations

Differentially-Private Hierarchical Clustering with Provable Approximation Guarantees

This work focuses on the stochastic block model, a popular model of graphs, and proposes a private 1 + o (1) approximation algorithm which also recovers the blocks exactly and meets the lower bound.

Correlation Clustering with Sherali-Adams

This paper affirmatively shows that there exists a $1.994-approximation algorithm based on $O(1/\varepsilon^{2})$ rounds of the Sherali-Adams hierarchy, and reaches an approximation ratio of $2+\varpsilon$ for CORRELATION CLUSTERING.

References

SHOWING 1-10 OF 47 REFERENCES

Better Private Algorithms for Correlation Clustering

This work revisits the correlation clustering under the differential privacy constraints and improves previous results and proposes a more involved algorithm which achieves an O ( n 1 . 5 ) additive error compared to the optimal cost in expectation on general graphs.

Differentially Private Correlation Clustering

An algorithm is proposed that achieves subquadratic additive error compared to the optimal cost and a lower bound is given showing that any pure differentially private algorithm for correlation clustering requires additive error of Ω(n).

Correlation Clustering in Constant Many Parallel Rounds

This work proposes a massively parallel computation (MPC) algorithm for correlation clustering that is considerably faster than prior work and is the first that can provably approximate a clustering problem on graphs using only a constant number of MPC rounds in the sublinear memory regime.

Differentially Private Clustering: Tight Approximation Ratios

Efficient differentially private algorithms that achieve essentially the same approximation ratios as those that can be obtained by any non-private algorithm, while incurring only small additive errors are given.

Differentially Private k-Means Clustering with Guaranteed Convergence

A novel differentially private clustering framework in the interactive settings which controls the orientation of the movement of the centroids over the iterations to ensure the convergence by injecting DP noise in a selected area is proposed.

Differentially Private Clustering in High-Dimensional Euclidean Spaces

This work gives differentially private and efficient algorithms achieving strong guarantees for k-means and k-median clustering when d = Ω(polylog(n), advancing the state-of-the-art result of √ dOPT+ poly(log n, d, k).

Differentially Private Densest Subgraph Detection

This work studies the densest subgraph problem in the edge privacy model, in which the edges of the graph are private, and presents the first sequential and parallel differentially private algorithms for this problem.

Correlation clustering in general weighted graphs

Locally Private k-Means in One Round

This algorithm is the first constant-factor approximation algorithm for k-means that requires only one round of communication in the local DP model, positively resolving an open question of Stemmer (2020).

Correlation clustering with a fixed number of clusters

This paper focuses on the situation when the number of clusters is stipulated to be a small constant k, and finds that for every k, there is a polynomial time approximation scheme for both maximizing agreements and minimizing disagreements.