Zhisong Pan

Anomaly detection in traffic using L1-norm minimization extreme learning machine

Machine learning algorithms are widely used for traffic classification and anomaly detection nowadays, however, how to fast and accurately classify the flows remains extremely challengeable. In this paper, we propose an extreme learning machine (ELM) based algorithm called L1-Norm Minimization ELM, which fully inherits the merits of ELM, and meanwhile, exhibits the sparsity-induced characteristics which could reduce the complexity of learning model. At the evaluation stage, we preprocessed the raw data trace from trans-Pacific backbone link between Japan and the United States, and generated 248 features datasets. The empirical study shows that L1-ELM can achieve good generalization performance on the evaluation datasets, while preserving the fast learning and little human intervened advantages that ELM has.

Network traffic classification via non-convex multi-task feature learning

Machine learning has been used in network traffic classification and statistical features are used to represent flows. However, conventional feature selection may work out in face of dynamic and complex traffic data. Multi-Task Learning has obtained quite wide attention nowadays, and one important form of multi-task learning is to exploit the features shared by tasks by sparse models. We propose a fast multi-task sparse feature learning method, using a non-convex Capped- ? 1 , ? 1 as the regularizer to learn a set of shared features in traffic data. Specifically, the non-convex multi-task feature learning model can learn features belonging to each task as well as the common features shared among tasks. We use the iterative shrinkage and thresholding (IST) algorithm to solve the problem, which has a closed-form solution for one of the crucial steps in the whole iteration. Experiment on real traffic data captured from backbone network as well as synthetic data and other popular real-world data show the effectiveness the method, compared with state-of-the-art methods.

Multi-label Text Categorization Using \(L_{21}\)-norm Minimization Extreme Learning Machine

Extreme learning machine (ELM) was extended from the generalized single hidden layer feedforward networks where the input weights of the hidden layer nodes can be assigned randomly. It has been widely used for its much faster learning speed and less manual works. Considering the field of multi-label text classification, in this paper, we propose an ELM based algorithm combined with \(L_{21}\)-norm minimization of the output weights matrix called \(L_{21}\)-norm Minimization ELM, which not only fully inherits the merits of ELM but also facilitates group sparsity and reduces complexity of the learning model. Extensive experiments on several benchmark data sets show a more desirable performance compared with other common multi-label classification algorithms.

Efficient Community Detection in Heterogeneous Social Networks

Community detection is of great importance which enables us to understand the network structure and promotes many real-world applications such as recommendation systems. The heterogeneous social networks, which contain multiple social relations and various user generated content, make the community detection problem more complicated. Particularly, social relations and user generated content are regarded as link information and content information, respectively. Since the two types of information indicate a common community structure from different perspectives, it is better to mine them jointly to improve the detection accuracy. Some detection algorithms utilizing both link and content information have been developed. However, most works take the private community structure of a single data source as the common one, and some methods take extra time transforming the content data into link data compared with mining directly. In this paper, we propose a framework based on regularized joint nonnegative matrix factorization (RJNMF) to utilize link and content information jointly to enhance the community detection accuracy. In the framework, we develop joint NMF to analyze link and content information simultaneously and introduce regularization to obtain the common community structure directly. Experimental results on real-world datasets show the effectiveness of our method.

Two-Dimensional Extreme Learning Machine

Extreme learning machine (ELM) has achieved wide attention due to faster learning speed compared with conventional neural network models like support vector machine (SVM) and back-propagation (BP) networks. However, like many other methods, ELM is originally proposed to handle vector pattern while nonvector patterns in real applications need to be explored, such as image data. We propose the two-dimensional extreme learning machine (2DELM) based on the very natural idea to deal with matrix data directly. Unlike original ELM which handles vectors, 2DELM take the matrices as input features without vectorization. Empirical studies on several real image datasets show the efficiency and effectiveness of the algorithm.

Extracting active modules from multilayer PPI network: a continuous optimization approach

Active modules identification has received much attention due to its ability to reveal regulatory and signaling mechanisms of a given cellular response. Most existing algorithms identify active modules by extracting connected nodes with high activity scores from a graph. These algorithms do not consider other topological properties such as community structure, which may correspond to functional units. In this paper, we propose an active module identification algorithm based on a novel objective function, which considers both and network topology and nodes activity. This objective is formulated as a constrained quadratic programming problem, which is convex and can be solved by iterative methods. Furthermore, the framework is extended to the multilayer dynamic PPI networks. Empirical results on the single layer and multilayer PPI networks show the effectiveness of proposed algorithms. Availability: The package and code for reproducing all results and figures are available at https://github.com/fairmiracle/ModuleExtraction.

Graph Classification Based on Sparse Graph Feature Selection and Extreme Learning Machine

Identification and classification of graph data is a hot research issue in pattern recognition. The conventional methods of graph classification usually convert the graph data to vector representation which ignore the sparsity of graph data. In this paper, we propose a new graph classification algorithm called graph classification based on sparse graph feature selection and extreme learning machine. The key of our method is using lasso to select sparse feature because of the sparsity of the corresponding feature space of the graph data, and extreme learning machine (ELM) is introduced to the following classification task due to its good performance. Extensive experimental results on a series of benchmark graph datasets validate the effectiveness of the proposed methods.

MODA: MOdule Differential Analysis for weighted gene co-expression network

Gene co-expression network differential analysis is designed to help biologists understand gene expression patterns under different conditions. We have implemented an R package called MODA (Module Differential Analysis) for gene co-expression network differential analysis. Based on transcriptomic data, MODA can be used to estimate and construct condition-specific gene co-expression networks, and identify differentially expressed subnetworks as conserved or condition specific modules which are potentially associated with relevant biological processes. The usefulness of the method is also demonstrated by synthetic data as well as Daphnia magna gene expression data under different environmental stresses.

Link Prediction via Sparse Gaussian Graphical Model

Link prediction is an important task in complex network analysis. Traditional link prediction methods are limited by network topology and lack of node property information, which makes predicting links challenging. In this study, we address link prediction using a sparse Gaussian graphical model and demonstrate its theoretical and practical effectiveness. In theory, link prediction is executed by estimating the inverse covariance matrix of samples to overcome information limits. The proposed method was evaluated with four small and four large real-world datasets. The experimental results show that the area under the curve (AUC) value obtained by the proposed method improved by an average of 3% and 12.5% compared to 13 mainstream similarity methods, respectively. This method outperforms the baseline method, and the prediction accuracy is superior to mainstream methods when using only 80% of the training set. The method also provides significantly higher AUC values when using only 60% in Dolphin and Taro datasets. Furthermore, the error rate of the proposed method demonstrates superior performance with all datasets compared to mainstream methods.

Detecting communities from multilayer networks: an aggregation approach

The study of multilayer networks has received much attention in network science in recent years. As a fundamental topic of network analysis, communities detection has been intensively studied on single networks. It is natural to extend communities detection to multilayer networks. In this paper, we propose an aggregation approach to detect communities from multiple networks. This approach simply constructs a consensus graph from multiple networks then applies existing communities detection algorithms on this consensus graph. We show the rationale behind this operation by both theoretical validation as well as experiments on multilayer networks, including the multilayer dynamic protein-protein interaction networks and a set of heterogenous biological networks.