The Experts below are selected from a list of 247419 Experts worldwide ranked by ideXlab platform
Michael Small - One of the best experts on this subject based on the ideXlab platform.
-
subspace based Network Community detection using sparse linear coding
International Conference on Data Engineering, 2016Co-Authors: Arif Mahmood, Michael SmallAbstract:Information mining from Networks by identifying communities is an important problem across a number of research fields including social science, biology, physics, and medicine. Most existing Community detection algorithms are graph theoretic and lack the ability to detect accurate Community boundaries if the ratio of intra-Community to inter-Community links is low. Also, algorithms based on modularity maximization may fail to resolve communities smaller than a specific size if the Community size varies significantly. We propose a fundamentally different Community detection algorithm based on the fact that each Network Community spans a different subspace in the geodesic space. Therefore, each node can only be efficiently represented as a linear combination of nodes spanning the same subspace (Fig. 1). To make the process of Community detection more robust, we use sparse linear coding with l1 norm constraint. In order to find a Community label for each node, sparse spectral clustering algorithm is used. The proposed Community detection technique is compared with more than ten state of the art methods on two benchmark Networks (with known clusters) using normalized mutual information criterion. Our proposed algorithm outperformed existing methods with a significant margin on both benchmark Networks.
-
subspace based Network Community detection using sparse linear coding
IEEE Transactions on Knowledge and Data Engineering, 2016Co-Authors: Arif Mahmood, Michael SmallAbstract:Information mining from Networks by identifying communities is an important problem across a number of research fields including social science, biology, physics, and medicine. Most existing Community detection algorithms are graph theoretic and lack the ability to detect accurate Community boundaries if the ratio of intra-Community to inter-Community links is low. Also, algorithms based on modularity maximization may fail to resolve communities smaller than a specific size if the Community size varies significantly. In this paper, we present a fundamentally different Community detection algorithm based on the fact that each Network Community spans a different subspace in the geodesic space. Therefore, each node can only be efficiently represented as a linear combination of nodes spanning the same subspace. To make the process of Community detection more robust, we use sparse linear coding with $\ell _1$ norm constraint. In order to find a Community label for each node, sparse spectral clustering algorithm is used. The proposed Community detection technique is compared with more than 10 state of the art methods on two benchmark Networks (with known clusters) using normalized mutual information criterion. Our proposed algorithm outperformed existing algorithms with a significant margin on both benchmark Networks. The proposed algorithm has also shown excellent performance on three real-world Networks.
Arif Mahmood - One of the best experts on this subject based on the ideXlab platform.
-
subspace based Network Community detection using sparse linear coding
International Conference on Data Engineering, 2016Co-Authors: Arif Mahmood, Michael SmallAbstract:Information mining from Networks by identifying communities is an important problem across a number of research fields including social science, biology, physics, and medicine. Most existing Community detection algorithms are graph theoretic and lack the ability to detect accurate Community boundaries if the ratio of intra-Community to inter-Community links is low. Also, algorithms based on modularity maximization may fail to resolve communities smaller than a specific size if the Community size varies significantly. We propose a fundamentally different Community detection algorithm based on the fact that each Network Community spans a different subspace in the geodesic space. Therefore, each node can only be efficiently represented as a linear combination of nodes spanning the same subspace (Fig. 1). To make the process of Community detection more robust, we use sparse linear coding with l1 norm constraint. In order to find a Community label for each node, sparse spectral clustering algorithm is used. The proposed Community detection technique is compared with more than ten state of the art methods on two benchmark Networks (with known clusters) using normalized mutual information criterion. Our proposed algorithm outperformed existing methods with a significant margin on both benchmark Networks.
-
subspace based Network Community detection using sparse linear coding
IEEE Transactions on Knowledge and Data Engineering, 2016Co-Authors: Arif Mahmood, Michael SmallAbstract:Information mining from Networks by identifying communities is an important problem across a number of research fields including social science, biology, physics, and medicine. Most existing Community detection algorithms are graph theoretic and lack the ability to detect accurate Community boundaries if the ratio of intra-Community to inter-Community links is low. Also, algorithms based on modularity maximization may fail to resolve communities smaller than a specific size if the Community size varies significantly. In this paper, we present a fundamentally different Community detection algorithm based on the fact that each Network Community spans a different subspace in the geodesic space. Therefore, each node can only be efficiently represented as a linear combination of nodes spanning the same subspace. To make the process of Community detection more robust, we use sparse linear coding with $\ell _1$ norm constraint. In order to find a Community label for each node, sparse spectral clustering algorithm is used. The proposed Community detection technique is compared with more than 10 state of the art methods on two benchmark Networks (with known clusters) using normalized mutual information criterion. Our proposed algorithm outperformed existing algorithms with a significant margin on both benchmark Networks. The proposed algorithm has also shown excellent performance on three real-world Networks.
Jinho Kim - One of the best experts on this subject based on the ideXlab platform.
-
PAKDD Workshops - Social Network Community Detection Using Strongly Connected Components
Lecture Notes in Computer Science, 2014Co-Authors: Wookey Lee, James Jung-hoon Lee, Jinho KimAbstract:The hasty information growth of social Network poses the information searching efficiency trials for Network mining research. Social Network graphs and web graphs are huge sources of highly densely connected hypertext links so that the social Networks can be described by a directed graph. This kind of Network has inherent structural characteristics such as overly expanded, duplicated, connectedness, and circuit paths, which could generate serious challenges for structured searching for sub-Network isomorphism and Community detection. In this paper, an efficient searching algorithm is suggested to discover social Network communities for overcoming the circuit path issue embedded in the social Network environment. Experimental results indicate that the proposed algorithm has better performance than the traditional circuit searching algorithms in terms of the time complexity as well as performance criteria.
Aaron Clauset - One of the best experts on this subject based on the ideXlab platform.
-
evaluating overfit and underfit in models of Network Community structure
IEEE Transactions on Knowledge and Data Engineering, 2020Co-Authors: Amir Ghasemian, Homa Hosseinmardi, Aaron ClausetAbstract:A common graph mining task is Community detection, which seeks an unsupervised decomposition of a Network into groups based on statistical regularities in Network connectivity. Although many such algorithms exist, Community detection's No Free Lunch theorem implies that no algorithm can be optimal across all inputs. However, little is known in practice about how different algorithms over or underfit to real Networks, or how to reliably assess such behavior across algorithms. Here, we present a broad investigation of over and underfitting across 16 state-of-the-art Community detection algorithms applied to a novel benchmark corpus of 572 structurally diverse real-world Networks. We find that (i) algorithms vary widely in the number and composition of communities they find, given the same input; (ii) algorithms can be clustered into distinct high-level groups based on similarities of their outputs on real-world Networks; (iii) algorithmic differences induce wide variation in accuracy on link-based learning tasks; and, (iv) no algorithm is always the best at such tasks across all inputs. Finally, we quantify each algorithm's overall tendency to over or underfit to Network data using a theoretically principled diagnostic, and discuss the implications for future advances in Community detection.
-
evaluating overfit and underfit in models of Network Community structure
arXiv: Machine Learning, 2018Co-Authors: Amir Ghasemian, Homa Hosseinmardi, Aaron ClausetAbstract:A common data mining task on Networks is Community detection, which seeks an unsupervised decomposition of a Network into structural groups based on statistical regularities in the Network's connectivity. Although many methods exist, the No Free Lunch theorem for Community detection implies that each makes some kind of tradeoff, and no algorithm can be optimal on all inputs. Thus, different algorithms will over or underfit on different inputs, finding more, fewer, or just different communities than is optimal, and evaluation methods that use a metadata partition as a ground truth will produce misleading conclusions about general accuracy. Here, we present a broad evaluation of over and underfitting in Community detection, comparing the behavior of 16 state-of-the-art Community detection algorithms on a novel and structurally diverse corpus of 406 real-world Networks. We find that (i) algorithms vary widely both in the number of communities they find and in their corresponding composition, given the same input, (ii) algorithms can be clustered into distinct high-level groups based on similarities of their outputs on real-world Networks, and (iii) these differences induce wide variation in accuracy on link prediction and link description tasks. We introduce a new diagnostic for evaluating overfitting and underfitting in practice, and use it to roughly divide Community detection methods into general and specialized learning algorithms. Across methods and inputs, Bayesian techniques based on the stochastic block model and a minimum description length approach to regularization represent the best general learning approach, but can be outperformed under specific circumstances. These results introduce both a theoretically principled approach to evaluate over and underfitting in models of Network Community structure and a realistic benchmark by which new methods may be evaluated and compared.
Liu Li-xiong - One of the best experts on this subject based on the ideXlab platform.
-
Combined node and link attributes of social Network Community detection algorithm
Application Research of Computers, 2013Co-Authors: Liu Li-xiongAbstract:The traditional social Network Community detection algorithms generally lack of consideration of node and link attributes,and full expression using node and link attribute information model and mechanism.Aiming at this issue,this paper put forward a kind of combined nodes and links attribute social Network Community detection algorithm.This algorithm combined with node attributes similarity between nodes,link weights and link information,defined the similar weights,and,on this basis,combining condensation algorithm to realize the social Network of Community division.Experiments show that effect of this algorithm about social Network attribute is remarkable,obviously in attribute-distinct Community.
-
Communication Network Community DetectionAlgorithm Orienting Hierarchical Structure Analysis
Computer Engineering, 2011Co-Authors: Liu Li-xiongAbstract:In order to detect communication Community and analyze its hierarchical structure of a communication Network,this paper presents a Community detection algorithm based on reachable communication distance ordering.By building multi-resolution embedded tree of communication density,it can display the hierarchical structure and key members of a Community.Via pruning the embedded tree,computation complexity can be reduced in the process of Community detection and hierarchical structure analysis.Experimental results on artificially synthesized Network data and real Network data approve that the algorithm is effective.