2022
DOI: 10.1214/22-ejs1986
|View full text |Cite
|
Sign up to set email alerts
|

Sparse and smooth: Improved guarantees for spectral clustering in the dynamic stochastic block model

Abstract: In this paper, we analyze classical variants of the Spectral Clustering (SC) algorithm in the Dynamic Stochastic Block Model (DSBM). Existing results show that, in the relatively sparse case where the expected degree grows logarithmically with the number of nodes, guarantees in the static case can be extended to the dynamic case and yield improved error bounds when the DSBM is sufficiently smooth in time, that is, the communities do not change too much between two time steps. We improve over these results by d… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
4
0

Year Published

2023
2023
2023
2023

Publication Types

Select...
3

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(4 citation statements)
references
References 44 publications
0
4
0
Order By: Relevance
“…when the maximum expected node degree is of order log(n) or higher), the proportion of misclassified nodes tends to 0 with a probability that goes to 1 when the number of nodes n increases using spectral clustering. This result inspired the recent paper [37] which considers a Dynamic Stochastic Block Model where the communities can change with time. They provide direct connection between the density of the graph and its smoothness (which measures how much the graph changes with time).…”
Section: Algorithmic Methodsmentioning
confidence: 52%
“…when the maximum expected node degree is of order log(n) or higher), the proportion of misclassified nodes tends to 0 with a probability that goes to 1 when the number of nodes n increases using spectral clustering. This result inspired the recent paper [37] which considers a Dynamic Stochastic Block Model where the communities can change with time. They provide direct connection between the density of the graph and its smoothness (which measures how much the graph changes with time).…”
Section: Algorithmic Methodsmentioning
confidence: 52%
“…Traditional spectral clustering algorithms use the spectrum of the graph adjacency matrix to generate a compact representation of the graph connectivity (Lei, Rinaldo et al 2015;Qin and Rohe 2013). A line of work on static clustering algorithms uses the stochastic block model for graph connectivity (Abbe 2017), which more recent works have extended to a dynamic stochastic block model (Keriven and Vaiter 2020;Pensky, Zhang et al 2019). While these works do not distinguish between clusters with different transition probabilities, earlier models incorporate such heterogeneity (Xu 2015).…”
Section: Related Workmentioning
confidence: 99%
“…Accounting for historical node connections with a single decay rate parameter offers the advantage of interpretability: the decay rate quantifies the emphasis put on historically formed edges, which can be tuned for specific datasets. Yet while prior works have examined the optimal decay rate for stylized network models, they use a single decay rate for all edges (Keriven and Vaiter 2020). In practice, the optimal rate will likely vary, e.g., with higher decay rates for clusters with higher membership turnover where historical information might reflect outdated cluster memberships, making it less useful.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation