COEUS: Community detection via seed-set expansion on graph streams

Liakos, Panagiotis; Ntoulas, Alexandros; Delis, Alex

doi:10.1109/bigdata.2017.8257983

Cited by 18 publications

(24 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…But since LPA simply updates the label of a node according to the plurality vote of its neighbors, it suffers from the problem of randomness caused by random update order, which affects the accuracy and stability of the community. In recent years, considerable efforts have been put in improving the effectiveness and efficiency of community detection [25,26]. PPC (Personalized PageRank Clustering) [27] employs the inherent cluster exploratory property of random walks to reveal the clusters of a given graph, which combines random walks and modularity to reveal the clusters of a graph.…”

Section: Related Workmentioning

confidence: 99%

Effectively Detecting Communities by Adjusting Initial Structure via Cores

et al. 2019

View full text Add to dashboard Cite

Community detection is helpful to understand useful information in real-world networks by uncovering their natural structures. In this paper, we propose a simple but effective community detection algorithm, called ACC, which needs no heuristic search but has near-linear time complexity. ACC defines a novel similarity which is different from most common similarity definitions by considering not only common neighbors of two adjacent nodes but also their mutual exclusive degree. According to this similarity, ACC groups nodes together to obtain the initial community structure in the first step. In the second step, ACC adjusts the initial community structure according to cores discovered through a new local density which is defined as the influence of a node on its neighbors. The third step expands communities to yield the final community structure. To comprehensively demonstrate the performance of ACC, we compare it with seven representative state-of-the-art community detection algorithms, on small size networks with ground-truth community structures and relatively big-size networks without ground-truth community structures. Experimental results show that ACC outperforms the seven compared algorithms in most cases.

show abstract

Section: Related Workmentioning

confidence: 99%

Effectively Detecting Communities by Adjusting Initial Structure via Cores

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Community detection algorithms are regularly used in order to identify meaningful clusters in a graph and have been successfully proposed in the context of social networks for more than a decade now [16][17][18]. We have only recently seen the adoption of such techniques in biological settings.…”

Section: Introductionmentioning

confidence: 99%

PathWalks: Identifying pathway communities using a disease-related map of integrated information

Karatzas¹,

Zachariou

Bourdakou

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

AbstractUnderstanding disease underlying biological mechanisms and respective interactions remains an elusive, time consuming and costly task. The realization of computational methodologies that can propose pathway/mechanism communities and reveal respective relationships can be of great value as it can help expedite the process of identifying how perturbations in a single pathway can affect other pathways.Random walks is a stochastic approach that can be used for both efficient discovery of strong connections and identification of communities formed in networks. The approach has grown in popularity as it efficiently exposes key network components and reveals strong interactions among genes, proteins, metabolites, pathways and drugs. Using random walks in biology, we need to overcome two key challenges: 1) construct disease-specific biological networks by integrating information from available data sources as they become available, and 2) provide guidance to the walker so as it can follow plausible trajectories that comply with inherent biological constraints.In this work, we present a methodology called PathWalks, where a random walker crosses a pathway-to-pathway network under the guidance of a disease-related map. The latter is a gene network that we construct by integrating multi-source information regarding a specific disease. The most frequent trajectories highlight communities of pathways that are expected to be strongly related to the disease under study. We present maps for Alzheimer’s Disease and Idiopathic Pulmonary Fibrosis and we use them as case-studies for identifying pathway communities through the application of PathWalks.In the case of Alzheimer’s Disease, the most visited pathways are the “Alzheimer’s disease” and the “Calcium signaling” pathways which have indeed the strongest association with Alzheimer’s Disease. Interestingly however, in the top-20 visited pathways we identify the “Kaposi sarcoma-associated herpesvirus infection” (HHV-8) and the “Human papillomavirus infection” (HPV) pathways suggesting that viruses may be involved in the development and progression of Alzheimer’s. Similarly, most of the highlighted pathways in Idiopathic Pulmonary Fibrosis are backed by the bibliography. We establish that “MAPK signaling” and “Cytokine-cytokine receptor interaction” pathways are the most visited. However, the “NOD receptor signaling” pathway is also in the top-40 edges. In Idiopathic Pulmonary Fibrosis samples, increased NOD receptor signaling has been associated with augmented concentrations of certain strains of Streptococcus. Additional experimental evidence is required however to further explore and ascertain the above indications.

show abstract

“…In this era of big data, processing massive networks by considering it as a static graph poses a problem. Therefore, it is good to consider a data stream model, in which the edges of a graph is considered as streams [5].…”

Section: Problem Statementmentioning

confidence: 99%

“…Community participation of a node in a community is the fraction of its adjacent nodes in the graph that are part of the community [5].…”

Section: Community Participationmentioning

confidence: 99%

See 1 more Smart Citation

Online Local Communities

Murali

View full text Add to dashboard Cite

Online Local Communities by Mrudula Murali A community in a network is a group of nodes that are densely and closely connected to each other, get sparsely connected to the nodes outside the community. Finding communities in a large network helps solve many real-world problems. But detecting such communities in a complex network by focusing on the whole network is not feasible. Instead, we focus on finding communities around one or more seed node(s) of interest. Therefore, in this project, we find local communities. Moreover, we consider the online setting where the whole graph is unknown in the beginning and we get a stream of edges, i.e., pair of nodes, or a stream of higher order structures, i.e., triangles of nodes. We created a new dataset that consists of web pages and their links by using the Internet Archive. We extended an existing online local graph community detection algorithm, called COEUS, for higher order structures such as triangles of nodes. We provide experimental results and comparison of the existing method and our proposed method using two public datasets, the Amazon and the DBLP as well as for our new Webpages dataset. In the experimental results, we see that the proposed method performs better than the existing method for one out of three test cases for the public dataset but not for our Webpages dataset. This is because the Webpages dataset has a large number of nodes with degree 1 which poses a problem for modified COEUS because it takes triangles as an input stream.

show abstract

COEUS: Community detection via seed-set expansion on graph streams

Cited by 18 publications

References 25 publications

Effectively Detecting Communities by Adjusting Initial Structure via Cores

Effectively Detecting Communities by Adjusting Initial Structure via Cores

PathWalks: Identifying pathway communities using a disease-related map of integrated information

Online Local Communities

Contact Info

Product

Resources

About