Feng Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Feng Chen has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Chang-Tien Lu
Virginia Tech, Alexandria, USA
6 shared publications - Naren Ramakrishnan
Virginia Tech, Alexandria, USA
5 shared publications - Baojian Zhou
Department of Computer Science University at Albany SUNY Albany NY USA
3 shared publications - Arnold P. Boedihardjo
U. S. Army Corps of Engineers Alexandria VA USA
2 shared publications - Jin-Hee Cho
Virginia Tech, Arlington, VA, USA
2 shared publications - Patrick Butler
Discovery Analytics Center Department of Computer Science Virginia Tech Arlington VA USA
2 shared publications
Latest Publications
- Open Access
Quantifying Classification Uncertainty using Regularized Evidential Neural Networks
Traditional deep neural nets (NNs) have shown the state-of-the-art performance in the task of classification in various applications. However, NNs have not considered any types of uncertainty associated with the class probabilities to minimize risk due to misclassification under uncertainty in real life. Unlike Bayesian neural nets indirectly infering uncertainty through weight uncertainties, evidential neural networks (ENNs) have been recently proposed to support explicit modeling of the uncertainty of class probabilities. It treats predictions of an NN as subjective opinions and learns the function by collecting the evidence leading to these opinions by a deterministic NN from data. However, an ENN is trained as a black box without explicitly considering different types of inherent data uncertainty, such as vacuity (uncertainty due to a lack of evidence) or dissonance (uncertainty due to conflicting evidence). This paper presents a new approach, called a {\em regularized ENN}, that learns an ENN based on regularizations related to different characteristics of inherent data uncertainty. Via the experiments with both synthetic and real-world datasets, we demonstrate that the proposed regularized ENN can better learn of an ENN modeling different types of uncertainty in the class probabilities for classification tasks.
Open AccessQuantifying Classification Uncertainty using Regularized Evidential Neural Networks
Traditional deep neural nets (NNs) have shown the state-of-the-art performance in the task of classification in various applications. However, NNs have not considered any types of uncertainty associated with the class probabilities to minimize risk due to misclassification under uncertainty in real life. Unlike Bayesian neural nets indirectly infering uncertainty through weight uncertainties, evidential neural networks (ENNs) have been recently proposed to support explicit modeling of the uncertainty of class probabilities. It treats predictions of an NN as subjective opinions and learns the function by collecting the evidence leading to these opinions by a deterministic NN from data. However, an ENN is trained as a black box without explicitly considering different types of inherent data uncertainty, such as vacuity (uncertainty due to a lack of evidence) or dissonance (uncertainty due to conflicting evidence). This paper presents a new approach, called a {\em regularized ENN}, that learns an ENN based on regularizations related to different characteristics of inherent data uncertainty. Via the experiments with both synthetic and real-world datasets, we demonstrate that the proposed regularized ENN can better learn of an ENN modeling different types of uncertainty in the class probabilities for classification tasks.
- Open Access
Deep Learning for Predicting Dynamic Uncertain Opinions in Network Data
Subjective Logic (SL) is one of well-known belief models that can explicitly deal with uncertain opinions and infer unknown opinions based on a rich set of operators of fusing multiple opinions. Due to high simplicity and applicability, SL has been substantially applied in a variety of decision making in the area of cybersecurity, opinion models, trust models, and/or social network analysis. However, SL and its variants have exposed limitations in predicting uncertain opinions in real-world dynamic network data mainly in three-fold: (1) a lack of scalability to deal with a large-scale network; (2) limited capability to handle heterogeneous topological and temporal dependencies among node-level opinions; and (3) a high sensitivity with conflicting evidence that may generate counterintuitive opinions derived from the evidence. In this work, we proposed a novel deep learning (DL)-based dynamic opinion inference model while node-level opinions are still formalized based on SL meaning that an opinion has a dimension of uncertainty in addition to belief and disbelief in a binomial opinion (i.e., agree or disagree). The proposed DL-based dynamic opinion inference model overcomes the above three limitations by integrating the following techniques: (1) state-of-the-art DL techniques, such as the Graph Convolutional Network (GCN) and the Gated Recurrent Units (GRU) for modeling the topological and temporal heterogeneous dependency information of a given dynamic network; (2) modeling conflicting opinions based on robust statistics; and (3) a highly scalable inference algorithm to predict dynamic, uncertain opinions in a linear computation time. We validated the outperformance of our proposed DL-based algorithm (i.e., GCN-GRU-opinion model) via extensive comparative performance analysis based on four real-world datasets.
Open AccessDeep Learning for Predicting Dynamic Uncertain Opinions in Network Data
Subjective Logic (SL) is one of well-known belief models that can explicitly deal with uncertain opinions and infer unknown opinions based on a rich set of operators of fusing multiple opinions. Due to high simplicity and applicability, SL has been substantially applied in a variety of decision making in the area of cybersecurity, opinion models, trust models, and/or social network analysis. However, SL and its variants have exposed limitations in predicting uncertain opinions in real-world dynamic network data mainly in three-fold: (1) a lack of scalability to deal with a large-scale network; (2) limited capability to handle heterogeneous topological and temporal dependencies among node-level opinions; and (3) a high sensitivity with conflicting evidence that may generate counterintuitive opinions derived from the evidence. In this work, we proposed a novel deep learning (DL)-based dynamic opinion inference model while node-level opinions are still formalized based on SL meaning that an opinion has a dimension of uncertainty in addition to belief and disbelief in a binomial opinion (i.e., agree or disagree). The proposed DL-based dynamic opinion inference model overcomes the above three limitations by integrating the following techniques: (1) state-of-the-art DL techniques, such as the Graph Convolutional Network (GCN) and the Gated Recurrent Units (GRU) for modeling the topological and temporal heterogeneous dependency information of a given dynamic network; (2) modeling conflicting opinions based on robust statistics; and (3) a highly scalable inference algorithm to predict dynamic, uncertain opinions in a linear computation time. We validated the outperformance of our proposed DL-based algorithm (i.e., GCN-GRU-opinion model) via extensive comparative performance analysis based on four real-world datasets.
- 31 August 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 31 (10) , 1849-1862
A Nonparametric Approach to Uncovering Connected Anomalies by Tree Shaped Priors
The area of anomaly detection has recently been expanded in the graph-based data. Anomalous vertices are always exhibited as a connected subgraph. Few works, however, have focused on connected anomalous subgraph detection because of the challenge of optimizing graph functionals under connectivity constraints. We employ the Non-Parametric Graph Scan (NPGS) statistics for capturing the anomalies within graph-based data. Based on the NPGS statistics, we proposed an efficient approximate algorithm that has provable guarantees on the performance and quality to address the connected anomalous subgraph detection problem. This algorithm consists of two steps: 1) First we decompose the problem into a sequence of subproblems, each of which can be reduced to a Budget Price-Collecting Steiner Tree (B-PCST) problem, and then propose a polynomial-time approximation algorithm for each subproblems; 2) We further develop the other efficient approximate algorithms in satisfying the connectivity constraints, where the connectivity constraints can be reformulated in a fixed tree topology within the special category of graph data. Our method has a wide variety of applications, such as disease outbreak detection, road traffic congestion detection, and event detection in social media, because the NPGS statistics is free of distribution assumptions and can be applied to heterogeneous graph data.
- 31 August 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 31 (10) , 1849-1862
A Nonparametric Approach to Uncovering Connected Anomalies by Tree Shaped Priors
The area of anomaly detection has recently been expanded in the graph-based data. Anomalous vertices are always exhibited as a connected subgraph. Few works, however, have focused on connected anomalous subgraph detection because of the challenge of optimizing graph functionals under connectivity constraints. We employ the Non-Parametric Graph Scan (NPGS) statistics for capturing the anomalies within graph-based data. Based on the NPGS statistics, we proposed an efficient approximate algorithm that has provable guarantees on the performance and quality to address the connected anomalous subgraph detection problem. This algorithm consists of two steps: 1) First we decompose the problem into a sequence of subproblems, each of which can be reduced to a Budget Price-Collecting Steiner Tree (B-PCST) problem, and then propose a polynomial-time approximation algorithm for each subproblems; 2) We further develop the other efficient approximate algorithms in satisfying the connectivity constraints, where the connectivity constraints can be reformulated in a fixed tree topology within the special category of graph data. Our method has a wide variety of applications, such as disease outbreak detection, road traffic congestion detection, and event detection in social media, because the NPGS statistics is free of distribution assumptions and can be applied to heterogeneous graph data.
- Open Access
Rational Neural Networks for Approximating Jump Discontinuities of Graph Convolution Operator
For node level graph encoding, a recent important state-of-art method is the graph convolutional networks (GCN), which nicely integrate local vertex features and graph topology in the spectral domain. However, current studies suffer from several drawbacks: (1) graph CNNs relies on Chebyshev polynomial approximation which results in oscillatory approximation at jump discontinuities; (2) Increasing the order of Chebyshev polynomial can reduce the oscillations issue, but also incurs unaffordable computational cost; (3) Chebyshev polynomials require degree $\Omega$(poly(1/$\epsilon$)) to approximate a jump signal such as $|x|$, while rational function only needs $\mathcal{O}$(poly log(1/$\epsilon$))\cite{liang2016deep,telgarsky2017neural}. However, it's non-trivial to apply rational approximation without increasing computational complexity due to the denominator. In this paper, the superiority of rational approximation is exploited for graph signal recovering. RatioanlNet is proposed to integrate rational function and neural networks. We show that rational function of eigenvalues can be rewritten as a function of graph Laplacian, which can avoid multiplication by the eigenvector matrix. Focusing on the analysis of approximation on graph convolution operation, a graph signal regression task is formulated. Under graph signal regression task, its time complexity can be significantly reduced by graph Fourier transform. To overcome the local minimum problem of neural networks model, a relaxed Remez algorithm is utilized to initialize the weight parameters. Convergence rate of RatioanlNet and polynomial based methods on jump signal is analyzed for a theoretical guarantee. The extensive experimental results demonstrated that our approach could effectively characterize the jump discontinuities, outperforming competing methods by a substantial margin on both synthetic and real-world graphs.Open AccessRational Neural Networks for Approximating Jump Discontinuities of Graph Convolution Operator
For node level graph encoding, a recent important state-of-art method is the graph convolutional networks (GCN), which nicely integrate local vertex features and graph topology in the spectral domain. However, current studies suffer from several drawbacks: (1) graph CNNs relies on Chebyshev polynomial approximation which results in oscillatory approximation at jump discontinuities; (2) Increasing the order of Chebyshev polynomial can reduce the oscillations issue, but also incurs unaffordable computational cost; (3) Chebyshev polynomials require degree $\Omega$(poly(1/$\epsilon$)) to approximate a jump signal such as $|x|$, while rational function only needs $\mathcal{O}$(poly log(1/$\epsilon$))\cite{liang2016deep,telgarsky2017neural}. However, it's non-trivial to apply rational approximation without increasing computational complexity due to the denominator. In this paper, the superiority of rational approximation is exploited for graph signal recovering. RatioanlNet is proposed to integrate rational function and neural networks. We show that rational function of eigenvalues can be rewritten as a function of graph Laplacian, which can avoid multiplication by the eigenvector matrix. Focusing on the analysis of approximation on graph convolution operation, a graph signal regression task is formulated. Under graph signal regression task, its time complexity can be significantly reduced by graph Fourier transform. To overcome the local minimum problem of neural networks model, a relaxed Remez algorithm is utilized to initialize the weight parameters. Convergence rate of RatioanlNet and polynomial based methods on jump signal is analyzed for a theoretical guarantee. The extensive experimental results demonstrated that our approach could effectively characterize the jump discontinuities, outperforming competing methods by a substantial margin on both synthetic and real-world graphs. - 30 August 2018
- Published by Springer Nature in Journal of Healthcare Informatics Research
- Vol. 3 (1) , 19-42
Bi-submodular Optimization (BSMO) for Detecting Drug-Drug Interactions (DDIs) from On-line Health Forums
Online health discussion forums as information exchange repository are used by different patient groups for sharing experience and seeking advice. Their accessibility is tremendously expanded in the last decade with the rapid growth of mobile internet. Among many popular topics, “drug-drug interactions” (DDIs) forum embeds a large number of DDIs hazards patient experienced however not published. In this paper, we intend to uncover the potential DDIs from the online forums and formulate the task as a sub-graph detection problem, such that co-mentioned drugs and symptoms are modeled as vertices, along with the occurrences are modeled as weighted edges. Therefore, a connected sub-graph consisting of both symptoms and drug vertices reveals DDIs occurrence. We then propose a novel bi-submodular function to characterize the likelihood of DDI occurrence within a connected sub-graph and apply an approximated algorithm to resolve the bi-submodular optimization (BSMO). The complexity of the algorithm is nearly linear. Our extensive experiments demonstrate the effectiveness and efficiency of the proposed approach.
- 30 August 2018
- Published by Springer Nature in Journal of Healthcare Informatics Research
- Vol. 3 (1) , 19-42
Bi-submodular Optimization (BSMO) for Detecting Drug-Drug Interactions (DDIs) from On-line Health Forums
Online health discussion forums as information exchange repository are used by different patient groups for sharing experience and seeking advice. Their accessibility is tremendously expanded in the last decade with the rapid growth of mobile internet. Among many popular topics, “drug-drug interactions” (DDIs) forum embeds a large number of DDIs hazards patient experienced however not published. In this paper, we intend to uncover the potential DDIs from the online forums and formulate the task as a sub-graph detection problem, such that co-mentioned drugs and symptoms are modeled as vertices, along with the occurrences are modeled as weighted edges. Therefore, a connected sub-graph consisting of both symptoms and drug vertices reveals DDIs occurrence. We then propose a novel bi-submodular function to characterize the likelihood of DDI occurrence within a connected sub-graph and apply an approximated algorithm to resolve the bi-submodular optimization (BSMO). The complexity of the algorithm is nearly linear. Our extensive experiments demonstrate the effectiveness and efficiency of the proposed approach.
- 27 June 2018
- Published by Springer Nature in GeoInformatica
- Vol. 22 (3) , 503-506
Preface: special issue on geo-social media analytics
- 27 June 2018
- Published by Springer Nature in GeoInformatica
- Vol. 22 (3) , 503-506
Preface: special issue on geo-social media analytics
- 25 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Proceedings of the IEEE
- Vol. 106 (5) , 829-845
Graph Anomaly Detection Based on Steiner Connectivity and Density
Detecting “hotspots” and “anomalies” is a recurring problem with a wide range of applications, such as social network analysis, epidemiology, finance, and biosurveillance, among others. Networks are a common abstraction in these applications for representing complex relationships. Typically, these networks are dynamic-, i.e., they evolve over time. A number of methods have been proposed for anomaly detection in such dynamic network data sets, which are primarily based on changes in network properties. We provide a survey of the various formulations of anomaly detection in dynamic networks with a focus on “window-based” methods. Window-based methods first define a time window of past network snapshots to model normal behavior and then mark a snapshot as anomalous if it has significantly different patterns from those observed in the time window. We describe two classes of techniques: 1) generalizations of Steiner connectivity; and 2) dense subgraph mining. Both have been used extensively in window-based graph anomaly detection. We summarize the key problem formulations that have been studied using these approaches, and we describe details of some of the main techniques.
- 25 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Proceedings of the IEEE
- Vol. 106 (5) , 829-845
Graph Anomaly Detection Based on Steiner Connectivity and Density
Detecting “hotspots” and “anomalies” is a recurring problem with a wide range of applications, such as social network analysis, epidemiology, finance, and biosurveillance, among others. Networks are a common abstraction in these applications for representing complex relationships. Typically, these networks are dynamic-, i.e., they evolve over time. A number of methods have been proposed for anomaly detection in such dynamic network data sets, which are primarily based on changes in network properties. We provide a survey of the various formulations of anomaly detection in dynamic networks with a focus on “window-based” methods. Window-based methods first define a time window of past network snapshots to model normal behavior and then mark a snapshot as anomalous if it has significantly different patterns from those observed in the time window. We describe two classes of techniques: 1) generalizations of Steiner connectivity; and 2) dense subgraph mining. Both have been used extensively in window-based graph anomaly detection. We summarize the key problem formulations that have been studied using these approaches, and we describe details of some of the main techniques.
- Open Access
Can Self-Censorship in News Media be Detected Algorithmically? A Case Study in Latin America
Censorship in social media has been well studied and provides insight into how governments stifle freedom of expression online. Comparatively less (or no) attention has been paid to detecting (self) censorship in traditional media (e.g., news) using social media as a bellweather. We present a novel unsupervised approach that views social media as a sensor to detect censorship in news media wherein statistically significant differences between information published in the news media and the correlated information published in social media are automatically identified as candidate censored events. We develop a hypothesis testing framework to identify and evaluate censored clusters of keywords, and a new near-linear-time algorithm (called GraphDPD) to identify the highest scoring clusters as indicators of censorship. We outline extensive experiments on semi-synthetic data as well as real datasets (with Twitter and local news media) from Mexico and Venezuela, highlighting the capability to accurately detect real-world self censorship events.
Open AccessCan Self-Censorship in News Media be Detected Algorithmically? A Case Study in Latin America
Censorship in social media has been well studied and provides insight into how governments stifle freedom of expression online. Comparatively less (or no) attention has been paid to detecting (self) censorship in traditional media (e.g., news) using social media as a bellweather. We present a novel unsupervised approach that views social media as a sensor to detect censorship in news media wherein statistically significant differences between information published in the news media and the correlated information published in social media are automatically identified as candidate censored events. We develop a hypothesis testing framework to identify and evaluate censored clusters of keywords, and a new near-linear-time algorithm (called GraphDPD) to identify the highest scoring clusters as indicators of censorship. We outline extensive experiments on semi-synthetic data as well as real datasets (with Twitter and local news media) from Mexico and Venezuela, highlighting the capability to accurately detect real-world self censorship events.
- Open Access
Technical Report: A Generalized Matching Pursuit Approach for Graph-Structured Sparsity
Sparsity-constrained optimization is an important and challenging problem that has wide applicability in data mining, machine learning, and statistics. In this paper, we focus on sparsity-constrained optimization in cases where the cost function is a general nonlinear function and, in particular, the sparsity constraint is defined by a graph-structured sparsity model. Existing methods explore this problem in the context of sparse estimation in linear models. To the best of our knowledge, this is the first work to present an efficient approximation algorithm, namely, Graph-structured Matching Pursuit (Graph-Mp), to optimize a general nonlinear function subject to graph-structured constraints. We prove that our algorithm enjoys the strong guarantees analogous to those designed for linear models in terms of convergence rate and approximation accuracy. As a case study, we specialize Graph-Mp to optimize a number of well-known graph scan statistic models for the connected subgraph detection task, and empirical evidence demonstrates that our general algorithm performs superior over state-of-the-art methods that are designed specifically for the task of connected subgraph detection.
Open AccessTechnical Report: A Generalized Matching Pursuit Approach for Graph-Structured Sparsity
Sparsity-constrained optimization is an important and challenging problem that has wide applicability in data mining, machine learning, and statistics. In this paper, we focus on sparsity-constrained optimization in cases where the cost function is a general nonlinear function and, in particular, the sparsity constraint is defined by a graph-structured sparsity model. Existing methods explore this problem in the context of sparse estimation in linear models. To the best of our knowledge, this is the first work to present an efficient approximation algorithm, namely, Graph-structured Matching Pursuit (Graph-Mp), to optimize a general nonlinear function subject to graph-structured constraints. We prove that our algorithm enjoys the strong guarantees analogous to those designed for linear models in terms of convergence rate and approximation accuracy. As a case study, we specialize Graph-Mp to optimize a number of well-known graph scan statistic models for the connected subgraph detection task, and empirical evidence demonstrates that our general algorithm performs superior over state-of-the-art methods that are designed specifically for the task of connected subgraph detection.
- 27 February 2016
- Published by Springer Nature in GeoInformatica
- Vol. 20 (4) , 879-921
The big data of violent events: algorithms for association analysis using spatio-temporal storytelling
- 27 February 2016
- Published by Springer Nature in GeoInformatica
- Vol. 20 (4) , 879-921
The big data of violent events: algorithms for association analysis using spatio-temporal storytelling