Zhaobin Kuang, Peggy Peissig, Vítor Santos Costa, Richard Maclin, David Page
Several prominent public health hazards [29] that occurred at the beginning of this century due to adverse drug events (ADEs) have raised international awareness of governments and industries about pharmacovigilance (PhV) [6,7], the science and activities to monitor and prevent adverse events caused by pharmaceutical products after they are introduced to the market. A major data source for PhV is large-scale longitudinal observational databases (LODs) [6] such as electronic health records (EHRs) and medical insurance claim databases. Inspired by the Self-Controlled Case Series (SCCS) model [27], arguably the leading method for ADE discovery from LODs, we propose baseline regularization, a regularized generalized linear model that leverages the diverse health profiles available in LODs across different individuals at different times. We apply the proposed method as well as SCCS to the Marshfield Clinic EHR. Experimental results suggest that the proposed method outperforms SCCS under various settings in identifying benchmark ADEs from the Observational Medical Outcomes Partnership ground truth [26].
{"title":"Pharmacovigilance via Baseline Regularization with Large-Scale Longitudinal Observational Data.","authors":"Zhaobin Kuang, Peggy Peissig, Vítor Santos Costa, Richard Maclin, David Page","doi":"10.1145/3097983.3097998","DOIUrl":"10.1145/3097983.3097998","url":null,"abstract":"<p><p>Several prominent public health hazards [29] that occurred at the beginning of this century due to adverse drug events (ADEs) have raised international awareness of governments and industries about pharmacovigilance (PhV) [6,7], the science and activities to monitor and prevent adverse events caused by pharmaceutical products after they are introduced to the market. A major data source for PhV is large-scale longitudinal observational databases (LODs) [6] such as electronic health records (EHRs) and medical insurance claim databases. Inspired by the Self-Controlled Case Series (SCCS) model [27], arguably the leading method for ADE discovery from LODs, we propose baseline regularization, a regularized generalized linear model that leverages the diverse health profiles available in LODs across different <i>individuals</i> at different <i>times</i>. We apply the proposed method as well as SCCS to the Marshfield Clinic EHR. Experimental results suggest that the proposed method outperforms SCCS under various settings in identifying <i>benchmark</i> ADEs from the Observational Medical Outcomes Partnership ground truth [26].</p>","PeriodicalId":74037,"journal":{"name":"KDD : proceedings. International Conference on Knowledge Discovery & Data Mining","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1145/3097983.3097998","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"36094259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
David Hallac, Sagar Vare, Stephen Boyd, Jure Leskovec
Subsequence clustering of multivariate time series is a useful tool for discovering repeated patterns in temporal data. Once these patterns have been discovered, seemingly complicated datasets can be interpreted as a temporal sequence of only a small number of states, or clusters. For example, raw sensor data from a fitness-tracking application can be expressed as a timeline of a select few actions (i.e., walking, sitting, running). However, discovering these patterns is challenging because it requires simultaneous segmentation and clustering of the time series. Furthermore, interpreting the resulting clusters is difficult, especially when the data is high-dimensional. Here we propose a new method of model-based clustering, which we call Toeplitz Inverse Covariance-based Clustering (TICC). Each cluster in the TICC method is defined by a correlation network, or Markov random field (MRF), characterizing the interdependencies between different observations in a typical subsequence of that cluster. Based on this graphical representation, TICC simultaneously segments and clusters the time series data. We solve the TICC problem through alternating minimization, using a variation of the expectation maximization (EM) algorithm. We derive closed-form solutions to efficiently solve the two resulting subproblems in a scalable way, through dynamic programming and the alternating direction method of multipliers (ADMM), respectively. We validate our approach by comparing TICC to several state-of-the-art baselines in a series of synthetic experiments, and we then demonstrate on an automobile sensor dataset how TICC can be used to learn interpretable clusters in real-world scenarios.
{"title":"Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Data.","authors":"David Hallac, Sagar Vare, Stephen Boyd, Jure Leskovec","doi":"10.1145/3097983.3098060","DOIUrl":"10.1145/3097983.3098060","url":null,"abstract":"<p><p>Subsequence clustering of multivariate time series is a useful tool for discovering repeated patterns in temporal data. Once these patterns have been discovered, seemingly complicated datasets can be interpreted as a temporal sequence of only a small number of states, or <i>clusters</i>. For example, raw sensor data from a fitness-tracking application can be expressed as a timeline of a select few actions (<i>i.e.</i>, walking, sitting, running). However, discovering these patterns is challenging because it requires simultaneous segmentation and clustering of the time series. Furthermore, interpreting the resulting clusters is difficult, especially when the data is high-dimensional. Here we propose a new method of model-based clustering, which we call <i>Toeplitz Inverse Covariance-based Clustering</i> (TICC). Each cluster in the TICC method is defined by a correlation network, or Markov random field (MRF), characterizing the interdependencies between different observations in a typical subsequence of that cluster. Based on this graphical representation, TICC simultaneously segments and clusters the time series data. We solve the TICC problem through alternating minimization, using a variation of the expectation maximization (EM) algorithm. We derive closed-form solutions to efficiently solve the two resulting subproblems in a scalable way, through dynamic programming and the alternating direction method of multipliers (ADMM), respectively. We validate our approach by comparing TICC to several state-of-the-art baselines in a series of synthetic experiments, and we then demonstrate on an automobile sensor dataset how TICC can be used to learn interpretable clusters in real-world scenarios.</p>","PeriodicalId":74037,"journal":{"name":"KDD : proceedings. International Conference on Knowledge Discovery & Data Mining","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5951184/pdf/nihms933926.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"36106210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yu Shi, Po-Wei Chan, Honglei Zhuang, Huan Gui, Jiawei Han
As a powerful representation paradigm for networked and multi-typed data, the heterogeneous information network (HIN) is ubiquitous. Meanwhile, defining proper relevance measures has always been a fundamental problem and of great pragmatic importance for network mining tasks. Inspired by our probabilistic interpretation of existing path-based relevance measures, we propose to study HIN relevance from a probabilistic perspective. We also identify, from real-world data, and propose to model cross-meta-path synergy, which is a characteristic important for defining path-based HIN relevance and has not been modeled by existing methods. A generative model is established to derive a novel path-based relevance measure, which is data-driven and tailored for each HIN. We develop an inference algorithm to find the maximum a posteriori (MAP) estimate of the model parameters, which entails non-trivial tricks. Experiments on two real-world datasets demonstrate the effectiveness of the proposed model and relevance measure.
{"title":"PReP: Path-Based Relevance from a Probabilistic Perspective in Heterogeneous Information Networks.","authors":"Yu Shi, Po-Wei Chan, Honglei Zhuang, Huan Gui, Jiawei Han","doi":"10.1145/3097983.3097990","DOIUrl":"https://doi.org/10.1145/3097983.3097990","url":null,"abstract":"<p><p>As a powerful representation paradigm for networked and multi-typed data, the heterogeneous information network (HIN) is ubiquitous. Meanwhile, defining proper relevance measures has always been a fundamental problem and of great pragmatic importance for network mining tasks. Inspired by our probabilistic interpretation of existing path-based relevance measures, we propose to study HIN relevance from a probabilistic perspective. We also identify, from real-world data, and propose to model <i>cross-meta-path synergy</i>, which is a characteristic important for defining path-based HIN relevance and has not been modeled by existing methods. A generative model is established to derive a novel path-based relevance measure, which is data-driven and tailored for each HIN. We develop an inference algorithm to find the maximum a posteriori (MAP) estimate of the model parameters, which entails non-trivial tricks. Experiments on two real-world datasets demonstrate the effectiveness of the proposed model and relevance measure.</p>","PeriodicalId":74037,"journal":{"name":"KDD : proceedings. International Conference on Knowledge Discovery & Data Mining","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1145/3097983.3097990","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"36496372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hao Yin, Austin R Benson, Jure Leskovec, David F Gleich
Local graph clustering methods aim to find a cluster of nodes by exploring a small region of the graph. These methods are attractive because they enable targeted clustering around a given seed node and are faster than traditional global graph clustering methods because their runtime does not depend on the size of the input graph. However, current local graph partitioning methods are not designed to account for the higher-order structures crucial to the network, nor can they effectively handle directed networks. Here we introduce a new class of local graph clustering methods that address these issues by incorporating higher-order network information captured by small subgraphs, also called network motifs. We develop the Motif-based Approximate Personalized PageRank (MAPPR) algorithm that finds clusters containing a seed node with minimal motif conductance, a generalization of the conductance metric for network motifs. We generalize existing theory to prove the fast running time (independent of the size of the graph) and obtain theoretical guarantees on the cluster quality (in terms of motif conductance). We also develop a theory of node neighborhoods for finding sets that have small motif conductance, and apply these results to the case of finding good seed nodes to use as input to the MAPPR algorithm. Experimental validation on community detection tasks in both synthetic and real-world networks, shows that our new framework MAPPR outperforms the current edge-based personalized PageRank methodology.
{"title":"Local Higher-Order Graph Clustering.","authors":"Hao Yin, Austin R Benson, Jure Leskovec, David F Gleich","doi":"10.1145/3097983.3098069","DOIUrl":"10.1145/3097983.3098069","url":null,"abstract":"<p><p>Local graph clustering methods aim to find a cluster of nodes by exploring a small region of the graph. These methods are attractive because they enable targeted clustering around a given seed node and are faster than traditional global graph clustering methods because their runtime does not depend on the size of the input graph. However, current local graph partitioning methods are not designed to account for the higher-order structures crucial to the network, nor can they effectively handle directed networks. Here we introduce a new class of local graph clustering methods that address these issues by incorporating higher-order network information captured by small subgraphs, also called network motifs. We develop the Motif-based Approximate Personalized PageRank (MAPPR) algorithm that finds clusters containing a seed node with minimal <i>motif conductance</i>, a generalization of the conductance metric for network motifs. We generalize existing theory to prove the fast running time (independent of the size of the graph) and obtain theoretical guarantees on the cluster quality (in terms of motif conductance). We also develop a theory of node neighborhoods for finding sets that have small motif conductance, and apply these results to the case of finding good seed nodes to use as input to the MAPPR algorithm. Experimental validation on community detection tasks in both synthetic and real-world networks, shows that our new framework MAPPR outperforms the current edge-based personalized PageRank methodology.</p>","PeriodicalId":74037,"journal":{"name":"KDD : proceedings. International Conference on Knowledge Discovery & Data Mining","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5951164/pdf/nihms933928.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"36106211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zhaobin Kuang, James Thomson, Michael Caldwell, Peggy Peissig, Ron Stewart, David Page
Computational Drug Repositioning (CDR) is the task of discovering potential new indications for existing drugs by mining large-scale heterogeneous drug-related data sources. Leveraging the patient-level temporal ordering information between numeric physiological measurements and various drug prescriptions provided in Electronic Health Records (EHRs), we propose a Continuous Self-controlled Case Series (CSCCS) model for CDR. As an initial evaluation, we look for drugs that can control Fasting Blood Glucose (FBG) level in our experiments. Applying CSCCS to the Marshfield Clinic EHR, well-known drugs that are indicated for controlling blood glucose level are rediscovered. Furthermore, some drugs with recent literature support for the potential effect of blood glucose level control are also identified.
{"title":"Computational Drug Repositioning Using Continuous Self-Controlled Case Series.","authors":"Zhaobin Kuang, James Thomson, Michael Caldwell, Peggy Peissig, Ron Stewart, David Page","doi":"10.1145/2939672.2939715","DOIUrl":"https://doi.org/10.1145/2939672.2939715","url":null,"abstract":"<p><p>Computational Drug Repositioning (CDR) is the task of discovering potential new indications for existing drugs by mining large-scale heterogeneous drug-related data sources. Leveraging the patient-level temporal ordering information between numeric physiological measurements and various drug prescriptions provided in Electronic Health Records (EHRs), we propose a Continuous Self-controlled Case Series (CSCCS) model for CDR. As an initial evaluation, we look for drugs that can control Fasting Blood Glucose (FBG) level in our experiments. Applying CSCCS to the Marshfield Clinic EHR, well-known drugs that are indicated for controlling blood glucose level are rediscovered. Furthermore, some drugs with recent literature support for the potential effect of blood glucose level control are also identified.</p>","PeriodicalId":74037,"journal":{"name":"KDD : proceedings. International Conference on Knowledge Discovery & Data Mining","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1145/2939672.2939715","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"34832807","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Recent statistical evidence has shown that a regression model by incorporating the interactions among the original covariates/features can significantly improve the interpretability for biological data. One major challenge is the exponentially expanded feature space when adding high-order feature interactions to the model. To tackle the huge dimensionality, hierarchical sparse models (HSM) are developed by enforcing sparsity under heredity structures in the interactions among the covariates. However, existing methods only consider pairwise interactions, making the discovery of important high-order interactions a non-trivial open problem. In this paper, we propose a generalized hierarchical sparse model (GHSM) as a generalization of the HSM models to tackle arbitrary-order interactions. The GHSM applies the ℓ1 penalty to all the model coefficients under a constraint that given any covariate, if none of its associated kth-order interactions contribute to the regression model, then neither do its associated higher-order interactions. The resulting objective function is non-convex with a challenge lying in the coupled variables appearing in the arbitrary-order hierarchical constraints and we devise an efficient optimization algorithm to directly solve it. Specifically, we decouple the variables in the constraints via both the general iterative shrinkage and thresholding (GIST) and the alternating direction method of multipliers (ADMM) methods into three subproblems, each of which is proved to admit an efficiently analytical solution. We evaluate the GHSM method in both synthetic problem and the antigenic sites identification problem for the influenza virus data, where we expand the feature space up to the 5th-order interactions. Empirical results demonstrate the effectiveness and efficiency of the proposed methods and the learned high-order interactions have meaningful synergistic covariate patterns in the influenza virus antigenicity.
{"title":"Generalized Hierarchical Sparse Model for Arbitrary-Order Interactive Antigenic Sites Identification in Flu Virus Data.","authors":"Lei Han, Yu Zhang, Xiu-Feng Wan, Tong Zhang","doi":"10.1145/2939672.2939786","DOIUrl":"https://doi.org/10.1145/2939672.2939786","url":null,"abstract":"<p><p>Recent statistical evidence has shown that a regression model by incorporating the interactions among the original covariates/features can significantly improve the interpretability for biological data. One major challenge is the exponentially expanded feature space when adding high-order feature interactions to the model. To tackle the huge dimensionality, hierarchical sparse models (HSM) are developed by enforcing sparsity under heredity structures in the interactions among the covariates. However, existing methods only consider pairwise interactions, making the discovery of important high-order interactions a non-trivial open problem. In this paper, we propose a generalized hierarchical sparse model (GHSM) as a generalization of the HSM models to tackle arbitrary-order interactions. The GHSM applies the ℓ<sub>1</sub> penalty to all the model coefficients under a constraint that given any covariate, if none of its associated <i>k</i>th-order interactions contribute to the regression model, then neither do its associated higher-order interactions. The resulting objective function is non-convex with a challenge lying in the coupled variables appearing in the arbitrary-order hierarchical constraints and we devise an efficient optimization algorithm to directly solve it. Specifically, we decouple the variables in the constraints via both the general iterative shrinkage and thresholding (GIST) and the alternating direction method of multipliers (ADMM) methods into three subproblems, each of which is proved to admit an efficiently analytical solution. We evaluate the GHSM method in both synthetic problem and the antigenic sites identification problem for the influenza virus data, where we expand the feature space up to the 5th-order interactions. Empirical results demonstrate the effectiveness and efficiency of the proposed methods and the learned high-order interactions have meaningful synergistic covariate patterns in the influenza virus antigenicity.</p>","PeriodicalId":74037,"journal":{"name":"KDD : proceedings. International Conference on Knowledge Discovery & Data Mining","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1145/2939672.2939786","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"34898415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wei Cheng, Kai Zhang, Haifeng Chen, Guofei Jiang, Zhengzhang Chen, Wei Wang
Modern world has witnessed a dramatic increase in our ability to collect, transmit and distribute real-time monitoring and surveillance data from large-scale information systems and cyber-physical systems. Detecting system anomalies thus attracts significant amount of interest in many fields such as security, fault management, and industrial optimization. Recently, invariant network has shown to be a powerful way in characterizing complex system behaviours. In the invariant network, a node represents a system component and an edge indicates a stable, significant interaction between two components. Structures and evolutions of the invariance network, in particular the vanishing correlations, can shed important light on locating causal anomalies and performing diagnosis. However, existing approaches to detect causal anomalies with the invariant network often use the percentage of vanishing correlations to rank possible casual components, which have several limitations: 1) fault propagation in the network is ignored; 2) the root casual anomalies may not always be the nodes with a high-percentage of vanishing correlations; 3) temporal patterns of vanishing correlations are not exploited for robust detection. To address these limitations, in this paper we propose a network diffusion based framework to identify significant causal anomalies and rank them. Our approach can effectively model fault propagation over the entire invariant network, and can perform joint inference on both the structural, and the time-evolving broken invariance patterns. As a result, it can locate high-confidence anomalies that are truly responsible for the vanishing correlations, and can compensate for unstructured measurement noise in the system. Extensive experiments on synthetic datasets, bank information system datasets, and coal plant cyber-physical system datasets demonstrate the effectiveness of our approach.
{"title":"Ranking Causal Anomalies via Temporal and Dynamical Analysis on Vanishing Correlations.","authors":"Wei Cheng, Kai Zhang, Haifeng Chen, Guofei Jiang, Zhengzhang Chen, Wei Wang","doi":"10.1145/2939672.2939765","DOIUrl":"https://doi.org/10.1145/2939672.2939765","url":null,"abstract":"<p><p>Modern world has witnessed a dramatic increase in our ability to collect, transmit and distribute real-time monitoring and surveillance data from large-scale information systems and cyber-physical systems. Detecting system anomalies thus attracts significant amount of interest in many fields such as security, fault management, and industrial optimization. Recently, invariant network has shown to be a powerful way in characterizing complex system behaviours. In the invariant network, a node represents a system component and an edge indicates a stable, significant interaction between two components. Structures and evolutions of the invariance network, in particular the vanishing correlations, can shed important light on locating causal anomalies and performing diagnosis. However, existing approaches to detect causal anomalies with the invariant network often use the percentage of vanishing correlations to rank possible casual components, which have several limitations: 1) fault propagation in the network is ignored; 2) the root casual anomalies may not always be the nodes with a high-percentage of vanishing correlations; 3) temporal patterns of vanishing correlations are not exploited for robust detection. To address these limitations, in this paper we propose a network diffusion based framework to identify significant causal anomalies and rank them. Our approach can effectively model fault propagation over the entire invariant network, and can perform joint inference on both the structural, and the time-evolving broken invariance patterns. As a result, it can locate high-confidence anomalies that are truly responsible for the vanishing correlations, and can compensate for unstructured measurement noise in the system. Extensive experiments on synthetic datasets, bank information system datasets, and coal plant cyber-physical system datasets demonstrate the effectiveness of our approach.</p>","PeriodicalId":74037,"journal":{"name":"KDD : proceedings. International Conference on Knowledge Discovery & Data Mining","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1145/2939672.2939765","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"35174806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The maximum likelihood estimation (MLE) for the Gaussian graphical model, which is also known as the inverse covariance estimation problem, has gained increasing interest recently. Most existing works assume that inverse covariance estimators contain sparse structure and then construct models with the ℓ1 regularization. In this paper, different from existing works, we study the inverse covariance estimation problem from another perspective by efficiently modeling the low-rank structure in the inverse covariance, which is assumed to be a combination of a low-rank part and a diagonal matrix. One motivation for this assumption is that the low-rank structure is common in many applications including the climate and financial analysis, and another one is that such assumption can reduce the computational complexity when computing its inverse. Specifically, we propose an efficient COmponent Pursuit (COP) method to obtain the low-rank part, where each component can be sparse. For optimization, the COP method greedily learns a rank-one component in each iteration by maximizing the log-likelihood. Moreover, the COP algorithm enjoys several appealing properties including the existence of an efficient solution in each iteration and the theoretical guarantee on the convergence of this greedy approach. Experiments on large-scale synthetic and real-world datasets including thousands of millions variables show that the COP method is faster than the state-of-the-art techniques for the inverse covariance estimation problem when achieving comparable log-likelihood on test data.
{"title":"Fast Component Pursuit for Large-Scale Inverse Covariance Estimation.","authors":"Lei Han, Yu Zhang, Tong Zhang","doi":"10.1145/2939672.2939851","DOIUrl":"https://doi.org/10.1145/2939672.2939851","url":null,"abstract":"<p><p>The maximum likelihood estimation (MLE) for the Gaussian graphical model, which is also known as the inverse covariance estimation problem, has gained increasing interest recently. Most existing works assume that inverse covariance estimators contain sparse structure and then construct models with the <i>ℓ</i><sub>1</sub> regularization. In this paper, different from existing works, we study the inverse covariance estimation problem from another perspective by efficiently modeling the low-rank structure in the inverse covariance, which is assumed to be a combination of a low-rank part and a diagonal matrix. One motivation for this assumption is that the low-rank structure is common in many applications including the climate and financial analysis, and another one is that such assumption can reduce the computational complexity when computing its inverse. Specifically, we propose an efficient COmponent Pursuit (COP) method to obtain the low-rank part, where each component can be sparse. For optimization, the COP method greedily learns a rank-one component in each iteration by maximizing the log-likelihood. Moreover, the COP algorithm enjoys several appealing properties including the existence of an efficient solution in each iteration and the theoretical guarantee on the convergence of this greedy approach. Experiments on large-scale synthetic and real-world datasets including thousands of millions variables show that the COP method is faster than the state-of-the-art techniques for the inverse covariance estimation problem when achieving comparable log-likelihood on test data.</p>","PeriodicalId":74037,"journal":{"name":"KDD : proceedings. International Conference on Knowledge Discovery & Data Mining","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1145/2939672.2939851","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"35060775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Convex optimization is an essential tool for modern data analysis, as it provides a framework to formulate and solve many problems in machine learning and data mining. However, general convex optimization solvers do not scale well, and scalable solvers are often specialized to only work on a narrow class of problems. Therefore, there is a need for simple, scalable algorithms that can solve many common optimization problems. In this paper, we introduce the network lasso, a generalization of the group lasso to a network setting that allows for simultaneous clustering and optimization on graphs. We develop an algorithm based on the Alternating Direction Method of Multipliers (ADMM) to solve this problem in a distributed and scalable manner, which allows for guaranteed global convergence even on large graphs. We also examine a non-convex extension of this approach. We then demonstrate that many types of problems can be expressed in our framework. We focus on three in particular - binary classification, predicting housing prices, and event detection in time series data - comparing the network lasso to baseline approaches and showing that it is both a fast and accurate method of solving large optimization problems.
{"title":"Network Lasso: Clustering and Optimization in Large Graphs.","authors":"David Hallac, Jure Leskovec, Stephen Boyd","doi":"10.1145/2783258.2783313","DOIUrl":"10.1145/2783258.2783313","url":null,"abstract":"<p><p>Convex optimization is an essential tool for modern data analysis, as it provides a framework to formulate and solve many problems in machine learning and data mining. However, general convex optimization solvers do not scale well, and scalable solvers are often specialized to only work on a narrow class of problems. Therefore, there is a need for simple, scalable algorithms that can solve many common optimization problems. In this paper, we introduce the <i>network lasso</i>, a generalization of the group lasso to a network setting that allows for simultaneous clustering and optimization on graphs. We develop an algorithm based on the Alternating Direction Method of Multipliers (ADMM) to solve this problem in a distributed and scalable manner, which allows for guaranteed global convergence even on large graphs. We also examine a non-convex extension of this approach. We then demonstrate that many types of problems can be expressed in our framework. We focus on three in particular - binary classification, predicting housing prices, and event detection in time series data - comparing the network lasso to baseline approaches and showing that it is both a fast and accurate method of solving large optimization problems.</p>","PeriodicalId":74037,"journal":{"name":"KDD : proceedings. International Conference on Knowledge Discovery & Data Mining","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1145/2783258.2783313","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"34655442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Marzyeh Ghassemi, Tristan Naumann, Finale Doshi-Velez, Nicole Brimmer, Rohit Joshi, Anna Rumshisky, Peter Szolovits
Accurate knowledge of a patient's disease state and trajectory is critical in a clinical setting. Modern electronic healthcare records contain an increasingly large amount of data, and the ability to automatically identify the factors that influence patient outcomes stand to greatly improve the efficiency and quality of care. We examined the use of latent variable models (viz. Latent Dirichlet Allocation) to decompose free-text hospital notes into meaningful features, and the predictive power of these features for patient mortality. We considered three prediction regimes: (1) baseline prediction, (2) dynamic (time-varying) outcome prediction, and (3) retrospective outcome prediction. In each, our prediction task differs from the familiar time-varying situation whereby data accumulates; since fewer patients have long ICU stays, as we move forward in time fewer patients are available and the prediction task becomes increasingly difficult. We found that latent topic-derived features were effective in determining patient mortality under three timelines: inhospital, 30 day post-discharge, and 1 year post-discharge mortality. Our results demonstrated that the latent topic features important in predicting hospital mortality are very different from those that are important in post-discharge mortality. In general, latent topic features were more predictive than structured features, and a combination of the two performed best. The time-varying models that combined latent topic features and baseline features had AUCs that reached 0.85, 0.80, and 0.77 for in-hospital, 30 day post-discharge and 1 year post-discharge mortality respectively. Our results agreed with other work suggesting that the first 24 hours of patient information are often the most predictive of hospital mortality. Retrospective models that used a combination of latent topic features and structured features achieved AUCs of 0.96, 0.82, and 0.81 for in-hospital, 30 day, and 1-year mortality prediction. Our work focuses on the dynamic (time-varying) setting because models from this regime could facilitate an on-going severity stratification system that helps direct care-staff resources and inform treatment strategies.
{"title":"Unfolding Physiological State: Mortality Modelling in Intensive Care Units.","authors":"Marzyeh Ghassemi, Tristan Naumann, Finale Doshi-Velez, Nicole Brimmer, Rohit Joshi, Anna Rumshisky, Peter Szolovits","doi":"10.1145/2623330.2623742","DOIUrl":"https://doi.org/10.1145/2623330.2623742","url":null,"abstract":"<p><p>Accurate knowledge of a patient's disease state and trajectory is critical in a clinical setting. Modern electronic healthcare records contain an increasingly large amount of data, and the ability to automatically identify the factors that influence patient outcomes stand to greatly improve the efficiency and quality of care. We examined the use of latent variable models (viz. Latent Dirichlet Allocation) to decompose free-text hospital notes into meaningful features, and the predictive power of these features for patient mortality. We considered three prediction regimes: (1) baseline prediction, (2) dynamic (time-varying) outcome prediction, and (3) retrospective outcome prediction. In each, our prediction task differs from the familiar time-varying situation whereby data accumulates; since fewer patients have long ICU stays, as we move forward in time fewer patients are available and the prediction task becomes increasingly difficult. We found that latent topic-derived features were effective in determining patient mortality under three timelines: inhospital, 30 day post-discharge, and 1 year post-discharge mortality. Our results demonstrated that the latent topic features important in predicting hospital mortality are very different from those that are important in post-discharge mortality. In general, latent topic features were more predictive than structured features, and a combination of the two performed best. The time-varying models that combined latent topic features and baseline features had AUCs that reached 0.85, 0.80, and 0.77 for in-hospital, 30 day post-discharge and 1 year post-discharge mortality respectively. Our results agreed with other work suggesting that the first 24 hours of patient information are often the most predictive of hospital mortality. Retrospective models that used a combination of latent topic features and structured features achieved AUCs of 0.96, 0.82, and 0.81 for in-hospital, 30 day, and 1-year mortality prediction. Our work focuses on the dynamic (time-varying) setting because models from this regime could facilitate an on-going severity stratification system that helps direct care-staff resources and inform treatment strategies.</p>","PeriodicalId":74037,"journal":{"name":"KDD : proceedings. International Conference on Knowledge Discovery & Data Mining","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1145/2623330.2623742","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"32724871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}