Instance-Optimal Cluster Recovery in the Labeled Stochastic Block Model
- URL: http://arxiv.org/abs/2306.12968v1
- Date: Sun, 18 Jun 2023 08:46:06 GMT
- Title: Instance-Optimal Cluster Recovery in the Labeled Stochastic Block Model
- Authors: Kaito Ariu, Alexandre Proutiere, Se-Young Yun
- Abstract summary: We devise an efficient algorithm that recovers clusters using the observed labels.
We present Instance-Adaptive Clustering (IAC), the first algorithm whose performance matches these lower bounds both in expectation and with high probability.
- Score: 79.46465138631592
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We consider the problem of recovering hidden communities in the Labeled
Stochastic Block Model (LSBM) with a finite number of clusters, where cluster
sizes grow linearly with the total number $n$ of items. In the LSBM, a label is
(independently) observed for each pair of items. Our objective is to devise an
efficient algorithm that recovers clusters using the observed labels. To this
end, we revisit instance-specific lower bounds on the expected number of
misclassified items satisfied by any clustering algorithm. We present
Instance-Adaptive Clustering (IAC), the first algorithm whose performance
matches these lower bounds both in expectation and with high probability. IAC
consists of a one-time spectral clustering algorithm followed by an iterative
likelihood-based cluster assignment improvement. This approach is based on the
instance-specific lower bound and does not require any model parameters,
including the number of clusters. By performing the spectral clustering only
once, IAC maintains an overall computational complexity of $\mathcal{O}(n
\text{polylog}(n))$. We illustrate the effectiveness of our approach through
numerical experiments.
Related papers
- Gap-Free Clustering: Sensitivity and Robustness of SDP [6.996002801232415]
We study graph clustering in the Block Model (SBM) in the presence of both large clusters and small, unrecoverable clusters.
Previous convex relaxation approaches achieving exact recovery do not allow any small clusters of size $o(sqrtn)$, or require a size gap between the smallest recovered cluster and the largest non-recovered cluster.
We provide an algorithm based on semidefinite programming (SDP) which removes these requirements and provably recovers large clusters regardless of the remaining cluster sizes.
arXiv Detail & Related papers (2023-08-29T21:27:21Z) - Recovering Unbalanced Communities in the Stochastic Block Model With
Application to Clustering with a Faulty Oracle [9.578056676899203]
oracle block model (SBM) is a fundamental model for studying graph clustering or community detection in networks.
We provide a simple SVD-based algorithm for recovering the communities in the SBM with communities of varying sizes.
arXiv Detail & Related papers (2022-02-17T08:51:19Z) - Optimal Clustering with Bandit Feedback [57.672609011609886]
This paper considers the problem of online clustering with bandit feedback.
It includes a novel stopping rule for sequential testing that circumvents the need to solve any NP-hard weighted clustering problem as its subroutines.
We show through extensive simulations on synthetic and real-world datasets that BOC's performance matches the lower boundally, and significantly outperforms a non-adaptive baseline algorithm.
arXiv Detail & Related papers (2022-02-09T06:05:05Z) - Personalized Federated Learning via Convex Clustering [72.15857783681658]
We propose a family of algorithms for personalized federated learning with locally convex user costs.
The proposed framework is based on a generalization of convex clustering in which the differences between different users' models are penalized.
arXiv Detail & Related papers (2022-02-01T19:25:31Z) - Lattice-Based Methods Surpass Sum-of-Squares in Clustering [98.46302040220395]
Clustering is a fundamental primitive in unsupervised learning.
Recent work has established lower bounds against the class of low-degree methods.
We show that, perhaps surprisingly, this particular clustering model textitdoes not exhibit a statistical-to-computational gap.
arXiv Detail & Related papers (2021-12-07T18:50:17Z) - On Margin-Based Cluster Recovery with Oracle Queries [22.672233769934845]
We study an active cluster recovery problem where, given a set of $n$ points oracle and an answering queries like "are these two points in the same cluster?"
We give an algorithm that recovers arbitrary convex clusters in exactly time, and with a number of queries that is lower than the best existing algorithm by $Theta(mm)$ factors.
For general pseudometric spaces, where clusters might not be convex or might not have any notion of shape, we give an algorithm that achieves the $O(log n)$ query bound, and is provably near optimal.
arXiv Detail & Related papers (2021-06-09T08:48:23Z) - Scalable Hierarchical Agglomerative Clustering [65.66407726145619]
Existing scalable hierarchical clustering methods sacrifice quality for speed.
We present a scalable, agglomerative method for hierarchical clustering that does not sacrifice quality and scales to billions of data points.
arXiv Detail & Related papers (2020-10-22T15:58:35Z) - Exact Recovery of Mangled Clusters with Same-Cluster Queries [20.03712152278538]
We study the cluster recovery problem in the semi-supervised active clustering framework.
We design an algorithm that, given $n$ points to be partitioned into $k$ clusters, uses $O(k3 ln k ln n)$ oracle queries and $tildeO(kn + k3)$ time to recover the clustering with zero misclassification error.
arXiv Detail & Related papers (2020-06-08T15:27:58Z) - Computationally efficient sparse clustering [67.95910835079825]
We provide a finite sample analysis of a new clustering algorithm based on PCA.
We show that it achieves the minimax optimal misclustering rate in the regime $|theta infty$.
arXiv Detail & Related papers (2020-05-21T17:51:30Z)
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.