Data Mining Practical Machine Learning Tools and Techniques

How to determine the community structure of complex networks is an open question. It is critical to establish the best strategies for community detection in networks of unknown structure. Here, using standard synthetic benchmarks, we show that none of the algorithms hitherto developed for community structure characterization perform optimally. Significantly, evaluating the results according to their modularity, the most popular measure of the quality of a partition, systematically provides mistaken solutions. However, a novel quality function, called Surprise, can be used to elucidate which is the optimal division into communities. Consequently, we show that the best strategy to find the community structure of all the networks examined involves choosing among the solutions provided by multiple algorithms the one with the highest Surprise value. We conclude that Surprise maximization precisely reveals the community structure of complex networks.

/pdf/surprise-maximization-reveals-the-community-structure-of-4cbionx4ar.pdf

Surprise maximization reveals the community structure of complex networks

Community detection, an important part of network analysis, has become a very popular field of research. This activity resulted in a profusion of community detection algorithms, all different in some not always clearly defined sense. This makes it very difficult to select an appropriate tool when facing the concrete task of having to identify and interpret groups of nodes, relatively to a system of interest. In this chapter, we tackle this problem in a very practical way, from the user’s point of view. We first review community detection algorithms and characterize them in terms of the nature of the communities they detect. We then focus on the methodological tools one can use to analyze the obtained community structure, both in terms of topological features and nodal attributes. To be as concrete as possible, we use a real-world social network to illustrate the application of the presented tools and give examples of interpretation of their results from a Business Science perspective.

/pdf/detection-and-interpretation-of-communities-in-complex-5btwjnsilu.pdf

Detection and Interpretation of Communities in Complex Networks: Practical Methods and Application

The ultimate goal of precision medicine is to determine right treatment for right patients based on precise diagnosis. To achieve this goal, correct stratification of patients using molecular features and clinical phenotypes is crucial. During the long history of medical science, our understanding on disease classification has been improved greatly by chemistry and molecular biology. Nowadays, we gain access to large scale patient-derived data by high-throughput technologies, generating a greater need for data science including unsupervised learning and network modeling. Unsupervised learning methods such as clustering could be a better solution to stratify patients when there is a lack of predefined classifiers. In network modularity analysis, clustering methods can be also applied to elucidate the complex structure of biological and disease networks at the systems level. In this review, we went over the main points of clustering analysis and network modeling, particularly in the context of Traditional Chinese medicine (TCM). We showed that this approach can provide novel insights on the rationale of classification for TCM herbs. In a case study, using a modularity analysis of multipartite networks, we illustrated that the TCM classifications are associated with the chemical properties of the herb ingredients. We concluded that multipartite network modeling may become a suitable data integration tool for understanding the mechanisms of actions of traditional medicine.

/pdf/unsupervised-learning-and-multipartite-network-models-a-53vw8jbk4l.pdf

Unsupervised Learning and Multipartite Network Models: A Promising Approach for Understanding Traditional Medicine

In the study of complex networks, a network is said to have community structure if it divides naturally into groups of nodes with dense connections within groups and only sparser connections between them [1]. Community structures are quite common in real networks. Social networks often include community groups based on common location, interests, occupation, etc. One of the most widely used methods for community detection is modularity maximization [2]. Modularity is a function that measures the quality of a particular division of a network into communities. But in [3], it is shown that communities that maximize the modularity are certainly groupings of smaller communities that need to be studied. In this work, we define a new function that qualifies a partition. We also present an algorithm that optimizes this function in order to find, within a reasonable time, the partition with the best measure of quality and which does not ignore small community.

An O(n2) algorithm for detecting communities of unbalanced sizes in large scale social networks

Despites the great interest caused by social networks in Business Science, their analysis is rarely performed in both a global and systematic way in this field This could be explained by the fact their practical extraction is a difficult and costly task One may ask if equivalent information could be retrieved from less expensive, individual data (ie describing single individuals instead of pairs) In this work, we try to address this question through group detection We gather both types of data from a population of students, estimate groups separately using individual and relational data, and obtain sets of clusters and communities, respectively We measure the overlap between clusters and communities, which turns out to be relatively weak We also define a predictive model, allowing us to identify the most discriminant attributes for the communities, and to reveal the presence of a tenuous link between the relational and individual data Our results indicate both types of data convey considerably different information in this specific context, and can therefore be considered as complementary To emphasize the interest of communities for Business Science, we also conduct an analysis based on hobbies and purchased brands

/pdf/informative-value-of-individual-and-relational-data-compared-57subanho2.pdf

Informative Value of Individual and Relational Data Compared Through Business-Oriented Community Detection

Despites the great interest caused by social networks in Business Science, their analysis is rarely performed both in a global and systematic way in this field: most authors focus on parts of the studied network, or on a few nodes considered individually. This could be explained by the fact that practical extraction of social networks is a difficult and costly task, since the specific relational data it requires are often difficult to access and thereby expensive. One may ask if equivalent information could be extracted from less expensive individual data, i.e. data concerning single individuals instead of several ones. In this work, we try to tackle this problem through group detection. We gather both types of data from a population of students, and estimate groups separately using individual and relational data, leading to sets of clusters and communities, respectively. We found out there is no strong overlapping between them, meaning both types of data do not convey the same information in this specific context, and can therefore be considered as complementary. However, a link, even if weak, exists and appears when we identify the most discriminant attributes relatively to the communities. Implications in Business Science include community prediction using individual data.

https://hal.archives-ouvertes.fr/hal-00633643/document

Business-Oriented Analysis of a Social Network of University Students: Informative Value of Individual and Relational Data Compared through Group Detection

Jean-Michel Balasque

Papers

Detection and Interpretation of Communities in Complex Networks: Practical Methods and Application

Informative Value of Individual and Relational Data Compared Through Business-Oriented Community Detection

Business-Oriented Analysis of a Social Network of University Students: Informative Value of Individual and Relational Data Compared through Group Detection

Business-oriented Analysis of a Social Network of University Students