Local Lanczos Spectral Approximation for Community Detection

@inproceedings{Shi2017LocalLS,
  title={Local Lanczos Spectral Approximation for Community Detection},
  author={Pan Shi and Kun He and David S. Bindel and John E. Hopcroft},
  booktitle={ECML/PKDD},
  year={2017}
}
We propose a novel approach called the Local Lanczos Spectral Approximation (LLSA) for identifying all latent members of a local community from very few seed members. To reduce the computation complexity, we first apply a fast heat kernel diffusing to sample a comparatively small subgraph covering almost all possible community members around the seeds. Then starting from a normalized indicator vector of the seeds and by a few steps of Lanczos iteration on the sampled subgraph, a local… 
Krylov Subspace Approximation for Local Community Detection in Large Networks
TLDR
The effectiveness of the proposed LOSP approach is theoretically analyzed based on Rayleigh quotients, and it is experimentally verified on a wide variety of real-world networks across social, production, and biological domains, as well as on an extensive set of synthetic LFR benchmark datasets.
Sparse Nonnegative Matrix Factorization for Multiple-Local-Community Detection
TLDR
This work presents a novel method of detecting multiple local communities to which a single-seed member belongs, using the sparseness generated by a sparse nonnegative matrix factorization (SNMF) to estimate the number of communities in the sampled subgraph.
A Hybrid Spectral Method for Network Community Detection
TLDR
Experimental results show that the proposed hybrid spectral method to effectively identify communities from networks can extract high-quality community structures from networks effectively.
p-Norm Flow Diffusion for Local Graph Clustering
TLDR
This work proposes a family of convex optimization formulations based on the idea of diffusion with p-norm network flow for local clustering and demonstrates the optimal solutions for these optimization problems and their usefulness in finding low conductance cuts around input seed set.
Density Sensitive Random Walk for Local Community Detection
TLDR
A density sensitive random walk algorithms (DSRW) for local community detection is proposed by integrating the graph density information into the random walk process, and the problems are resolved and the clustering result is improved.
Clustering of graph vertex subset via Krylov subspace model reduction
TLDR
Two novel algorithms for spectral clustering of a subset of the graph vertices (target subset) based on the theory of model order reduction rely on realizations of a reduced order model (ROM) that accurately approximates the diffusion transfer function of the original graph for inputs and outputs restricted to the target subset.
Neighbor Similarity Based Agglomerative Method for Community Detection in Networks
TLDR
The results show that the proposed node similarity based community detection method can detect high-quality community structures from networks steadily and efficiently and outperform the comparison algorithms significantly.
Detecting communities from networks using an improved self-organizing map
TLDR
A number of algorithms for detecting communities, some of which suffer from high complexity or need to be modified, are derived.
Statistical guarantees for local graph clustering
TLDR
It is shown that l1-regularized PageRank and approximate personalized PageRank (APPR), another very popular method for local graph clustering, are equivalent in the sense that one can lower and upper bound the output of one with theoutput of the other.
...
...

References

SHOWING 1-10 OF 39 REFERENCES
Detecting Overlapping Communities from Local Spectral Subspaces
TLDR
A systematic investigation on LOSP is provided, and it is demonstrated that LOSP outperforms the Heat Kernel and PageRank diffusions on large real world networks across multiple domains and addresses the problem of multiple membership identification.
Heat kernel based community detection
TLDR
This work presents the first deterministic, local algorithm to compute this type of graph diffusion and uses that algorithm to study the communities that it produces, indicating that the communities produced by this method have better conductance than those produced by PageRank, although they take slightly longer to compute.
Uncovering the Small Community Structure in Large Networks: A Local Spectral Approach
TLDR
A novel approach for finding overlapping communities called LEMON (Local Expansion via Minimum One Norm), which different from PageRank-like diffusion methods finds the community by seeking a sparse vector in the span of the local spectra such that the seeds are in its support.
DEMON: a local-first discovery method for overlapping communities
TLDR
A simple local-first approach to community discovery, able to unveil the modular organization of real complex networks, by democratically letting each node vote for the communities it sees surrounding it in its limited view of the global system.
Community membership identification from small seed sets
TLDR
This work evaluates several variants of seed expansion methods across multiple domains, using publicly available datasets with labeled, ground-truth communities, and explores topological properties of communities and seed sets that correlate with algorithm performance.
A local spectral method for graphs: with applications to improving graph partitions and exploring data graphs locally
TLDR
This paper introduces a locally-biased analogue of the second eigenvector of the Laplacian matrix, and demonstrates its usefulness at highlighting local properties of data graphs in a semi-supervised manner and shows how it can applied to finding locally- biased sparse cuts around an input vertex seed set in social and information networks.
A classification for community discovery methods in complex networks
TLDR
The aim of this survey is to provide a ‘user manual’ for the community discovery problem and to organize the main categories of community discovery methods based on the definition of community they adopt.
Benchmarks for testing community detection algorithms on directed and weighted graphs with overlapping communities.
TLDR
The basic ideas behind the previous benchmark are extended to generate directed and weighted networks with built-in community structure, and the possibility that nodes belong to more communities is considered, a feature occurring in real systems, such as social networks.
Benchmark graphs for testing community detection algorithms.
TLDR
This work introduces a class of benchmark graphs, that account for the heterogeneity in the distributions of node degrees and of community sizes, and uses this benchmark to test two popular methods of community detection, modularity optimization, and Potts model clustering.
A tutorial on spectral clustering
TLDR
This tutorial describes different graph Laplacians and their basic properties, present the most common spectral clustering algorithms, and derive those algorithms from scratch by several different approaches.
...
...