Results 1 - 10
of
415
Large scale multiple kernel learning
- JOURNAL OF MACHINE LEARNING RESEARCH
, 2006
"... While classical kernel-based learning algorithms are based on a single kernel, in practice it is often desirable to use multiple kernels. Lanckriet et al. (2004) considered conic combinations of kernel matrices for classification, leading to a convex quadratically constrained quadratic program. We s ..."
Abstract
-
Cited by 340 (20 self)
- Add to MetaCart
While classical kernel-based learning algorithms are based on a single kernel, in practice it is often desirable to use multiple kernels. Lanckriet et al. (2004) considered conic combinations of kernel matrices for classification, leading to a convex quadratically constrained quadratic program. We show that it can be rewritten as a semi-infinite linear program that can be efficiently solved by recycling the standard SVM implementations. Moreover, we generalize the formulation and our method to a larger class of problems, including regression and one-class classification. Experimental results show that the proposed algorithm works for hundred thousands of examples or hundreds of kernels to be combined, and helps for automatic model selection, improving the interpretability of the learning result. In a second part we discuss general speed up mechanism for SVMs, especially when used with sparse feature maps as appear for string kernels, allowing us to train a string kernel SVM on a 10 million real-world splice data set from computational biology. We integrated multiple kernel learning in our machine learning toolbox SHOGUN for which the source code is publicly available at
A support vector method for optimizing average precision
- In SIGIR ’07
, 2007
"... Machine learning is commonly used to improve ranked re-trieval systems. Due to computational difficulties, few learn-ing techniques have been developed to directly optimize for mean average precision (MAP), despite its widespread use in evaluating such systems. Existing approaches optimiz-ing MAP ei ..."
Abstract
-
Cited by 195 (7 self)
- Add to MetaCart
(Show Context)
Machine learning is commonly used to improve ranked re-trieval systems. Due to computational difficulties, few learn-ing techniques have been developed to directly optimize for mean average precision (MAP), despite its widespread use in evaluating such systems. Existing approaches optimiz-ing MAP either do not find a globally optimal solution, or are computationally expensive. In contrast, we present a general SVM learning algorithm that efficiently finds a globally optimal solution to a straightforward relaxation of MAP. We evaluate our approach using the TREC 9 and TREC 10 Web Track corpora (WT10g), comparing against SVMs optimized for accuracy and ROCArea. In most cases we show our method to produce statistically significant im-provements in MAP scores.
Differential expression in RNA-seq: A matter of depth
- GENOME RESEARCH
, 2011
"... Next Generation Sequencing (NGS) technologies are revolutionizing genome research and in particular, their application to transcriptomics (RNA-seq) is increasingly being used for gene expression profiling as a replacement for microarrays. However, the properties of RNA-seq data have not been yet ful ..."
Abstract
-
Cited by 99 (4 self)
- Add to MetaCart
Next Generation Sequencing (NGS) technologies are revolutionizing genome research and in particular, their application to transcriptomics (RNA-seq) is increasingly being used for gene expression profiling as a replacement for microarrays. However, the properties of RNA-seq data have not been yet fully established and additional research is needed for understanding how these data respond to differential expression analysis. In this work we set out to gain insights into the characteristics of RNA-seq data analysis by studying an important parameter of this technology: the sequencing depth. We have analyzed how sequencing depth affects the detection of transcripts and their identification as differentially expressed, looking at aspects such as transcript biotype, length, expression level and fold-change. We have evaluated different algorithms available for the analysis of RNA-seq and proposed a novel approach-NOISeq- that differs from existing methods in that it is data-adaptive and non-parametric. Our results reveal that most existing methodologies suffer from a strong dependency on sequencing depth for their differential expression calls and that this results in a considerable number of false positives that increases as the number of reads grows. In contrast, our proposed method models the noise distribution from the actual data, can therefore better adapt to the size of the dataset and is more effective in controlling the rate of false discoveries. This work discusses the true potential of RNA-seq for studying regulation at low expression ranges, the noise within RNA-seq data and the issue of replication.
Decision trees for hierarchical multi-label classification
- Machine Learning
, 2008
"... Abstract. Hierarchical multi-label classification (HMC) is a variant of classification where instances may belong to multiple classes at the same time and these classes are organized in a hierarchy. This article presents several approaches to the induction of decision trees for HMC, as well as an em ..."
Abstract
-
Cited by 59 (2 self)
- Add to MetaCart
(Show Context)
Abstract. Hierarchical multi-label classification (HMC) is a variant of classification where instances may belong to multiple classes at the same time and these classes are organized in a hierarchy. This article presents several approaches to the induction of decision trees for HMC, as well as an empirical study of their use in functional genomics. We compare learn-ing a single HMC tree (which makes predictions for all classes together) to two approaches that learn a set of regular classification trees (one for each class). The first approach defines an independent single-label clas-sification task for each class (SC). Obviously, the hierarchy introduces dependencies between the classes. While they are ignored by the first ap-proach, they are exploited by the second approach, named hierarchical single-label classification (HSC). Depending on the application at hand, the hierarchy of classes can be such that each class has at most one parent (tree structure) or such that classes may have multiple parents (DAG structure). The latter case has not been considered before and we show how the HMC and HSC approaches can be modified to support this setting. We compare the three approaches on 24 yeast data sets using as classification schemes MIPS’s FunCat (tree structure) and the Gene Ontology (DAG structure). We show that HMC trees outperform HSC and SC trees along three dimensions: predictive accuracy, model size, and induction time. We conclude that HMC trees should definitely be considered in HMC tasks where interpretable models are desired. 1
Discriminative Structure and Parameter Learning for Markov Logic Networks
"... Markov logic networks (MLNs) are an expressive representation for statistical relational learning that generalizes both first-order logic and graphical models. Existing methods for learning the logical structure of an MLN are not discriminative; however, many relational learning problems involve spe ..."
Abstract
-
Cited by 56 (5 self)
- Add to MetaCart
(Show Context)
Markov logic networks (MLNs) are an expressive representation for statistical relational learning that generalizes both first-order logic and graphical models. Existing methods for learning the logical structure of an MLN are not discriminative; however, many relational learning problems involve specific target predicates that must be inferred from given background information. We found that existing MLN methods perform very poorly on several such ILP benchmark problems, and we present improved discriminative methods for learning MLN clauses and weights that outperform existing MLN and traditional ILP methods. 1.
Evaluation of background subtraction techniques for video surveillance
- Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2011
"... IEEE Copyright Notice Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work i ..."
Abstract
-
Cited by 54 (1 self)
- Add to MetaCart
(Show Context)
IEEE Copyright Notice Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained
Factorizing YAGO: scalable machine learning for linked data
- In WWW
, 2012
"... Vast amounts of structured information have been published in the Semantic Web’s Linked Open Data (LOD) cloud and their size is still growing rapidly. Yet, access to this information via reasoning and querying is sometimes difficult, due to LOD’s size, partial data inconsistencies and inherent noisi ..."
Abstract
-
Cited by 49 (15 self)
- Add to MetaCart
(Show Context)
Vast amounts of structured information have been published in the Semantic Web’s Linked Open Data (LOD) cloud and their size is still growing rapidly. Yet, access to this information via reasoning and querying is sometimes difficult, due to LOD’s size, partial data inconsistencies and inherent noisiness. Machine Learning offers an alternative approach to exploiting LOD’s data with the advantages that Machine Learning algorithms are typically robust to both noise and data inconsistencies and are able to efficiently utilize nondeterministic dependencies in the data. From a Machine Learning point of view, LOD is challenging due to its relational nature and its scale. Here, we present an efficient approach to relational learning on LOD data, based on the factorization of a sparse tensor that scales to data consisting
SVMs Modeling for Highly Imbalanced Classification
, 2009
"... Traditional classification algorithms can be limited in their performance on highly unbalanced data sets. A popular stream of work for countering the problem of class imbalance has been the application of a sundry of sampling strategies. In this correspondence, we focus on designing modifications to ..."
Abstract
-
Cited by 44 (0 self)
- Add to MetaCart
(Show Context)
Traditional classification algorithms can be limited in their performance on highly unbalanced data sets. A popular stream of work for countering the problem of class imbalance has been the application of a sundry of sampling strategies. In this correspondence, we focus on designing modifications to support vector machines (SVMs) to appropriately tackle the problem of class imbalance. We incorporate different “rebalance ” heuristics in SVM modeling, including cost-sensitive learning, and over- and undersampling. These SVM-based strategies are compared with various state-of-the-art approaches on a variety of data sets by using various metrics, including G-mean, area under the receiver operating characteristic curve, F-measure, and area under the precision/recall curve. We show that we are able to surpass or match the previously known best algorithms on each data set. In particular, of the four SVM variations considered in this correspondence, the novel granular SVMs–repetitive undersampling algorithm (GSVM-RU) is the best in terms of both effectiveness and efficiency. GSVM-RU is effective, as it can minimize the negative effect of information loss while maximizing the positive effect of data cleaning in the undersampling process. GSVM-RU is efficient by extracting much less support vectors and, hence, greatly speeding up SVM prediction.
GeneNetWeaver: in silico benchmark generation and performance profiling of network inference methods
, 2011
"... Motivation: Over the last decade, numerous methods have been developed for inference of regulatory networks from gene expression data. However, accurate and systematic evaluation of these methods is hampered by the difficulty of constructing adequate benchmarks and the lack of tools for a differenti ..."
Abstract
-
Cited by 38 (0 self)
- Add to MetaCart
Motivation: Over the last decade, numerous methods have been developed for inference of regulatory networks from gene expression data. However, accurate and systematic evaluation of these methods is hampered by the difficulty of constructing adequate benchmarks and the lack of tools for a differentiated analysis of network predictions on such benchmarks. Results: Here, we describe a novel and comprehensive method for in silico benchmark generation and performance profiling of network inference methods available to the community as an open-source software called GeneNetWeaver (GNW). In addition to the generation of detailed dynamical models of gene regulatory networks to be used as benchmarks, GNW provides a network motif analysis that reveals systematic prediction errors, thereby indicating potential ways of improving inference methods. The accuracy of network inference methods is evaluated using standard metrics such as precision-recall and receiver operating characteristic curves. We show how GNW can be used to assess the performance and identify the strengths and weaknesses of six inference methods. Furthermore, we used GNW to provide the international Dialogue for Reverse Engineering Assessments and Methods (DREAM) competition with three network inference challenges (DREAM3, DREAM4 and DREAM5). Availability: GNW is available at
An Experimental Comparison of Performance Measures for Classification
, 2007
"... Performance metrics in classification are fundamental to assess the quality of learning methods and learned models. However, many different measures have been defined in the literature with the aim of making better choices in general or for a specific application area. Choices made by one metric are ..."
Abstract
-
Cited by 36 (7 self)
- Add to MetaCart
(Show Context)
Performance metrics in classification are fundamental to assess the quality of learning methods and learned models. However, many different measures have been defined in the literature with the aim of making better choices in general or for a specific application area. Choices made by one metric are claimed to be different from choices made by other metrics. In this work we analyse experimentally the behaviour of 18 different performance metrics in several scenarios, identifying clusters and relationships between measures. We also perform a sensitivity analysis for all of them in terms of several traits: class threshold choice, separability/ranking quality, calibration performance and sensitivity to changes in prior class distribution. From the definitions and the experiments, we give a comprehensive analysis on the relationships between metrics, and a taxonomy and arrangement of them according to the previous traits. This can be useful to choose the most adequate measure (or set of measures) for a specific application. Additionally, the study also highlights some niches in which new measures might be defined and also shows that some supposedly innovative measures make the same choices (or almost) than existing ones. Finally, this work can also be used as a reference for comparing experimental results in the pattern recognition and machine learning literature, when using different measures.
