Results 1  10
of
133
Cluster Ensembles  A Knowledge Reuse Framework for Combining Multiple Partitions
 Journal of Machine Learning Research
, 2002
"... This paper introduces the problem of combining multiple partitionings of a set of objects into a single consolidated clustering without accessing the features or algorithms that determined these partitionings. We first identify several application scenarios for the resultant 'knowledge reuse&ap ..."
Abstract

Cited by 603 (20 self)
 Add to MetaCart
(Show Context)
This paper introduces the problem of combining multiple partitionings of a set of objects into a single consolidated clustering without accessing the features or algorithms that determined these partitionings. We first identify several application scenarios for the resultant 'knowledge reuse' framework that we call cluster ensembles. The cluster ensemble problem is then formalized as a combinatorial optimization problem in terms of shared mutual information. In addition to a direct maximization approach, we propose three effective and efficient techniques for obtaining highquality combiners (consensus functions). The first combiner induces a similarity measure from the partitionings and then reclusters the objects. The second combiner is based on hypergraph partitioning. The third one collapses groups of clusters into metaclusters which then compete for each object to determine the combined clustering. Due to the low computational costs of our techniques, it is quite feasible to use a supraconsensus function that evaluates all three approaches against the objective function and picks the best solution for a given situation. We evaluate the effectiveness of cluster ensembles in three qualitatively different application scenarios: (i) where the original clusters were formed based on nonidentical sets of features, (ii) where the original clustering algorithms worked on nonidentical sets of objects, and (iii) where a common dataset is used and the main purpose of combining multiple clusterings is to improve the quality and robustness of the solution. Promising results are obtained in all three situations for synthetic as well as real datasets.
A Survey on Transfer Learning
"... A major assumption in many machine learning and data mining algorithms is that the training and future data must be in the same feature space and have the same distribution. However, in many realworld applications, this assumption may not hold. For example, we sometimes have a classification task i ..."
Abstract

Cited by 459 (24 self)
 Add to MetaCart
A major assumption in many machine learning and data mining algorithms is that the training and future data must be in the same feature space and have the same distribution. However, in many realworld applications, this assumption may not hold. For example, we sometimes have a classification task in one domain of interest, but we only have sufficient training data in another domain of interest, where the latter data may be in a different feature space or follow a different data distribution. In such cases, knowledge transfer, if done successfully, would greatly improve the performance of learning by avoiding much expensive data labeling efforts. In recent years, transfer learning has emerged as a new learning framework to address this problem. This survey focuses on categorizing and reviewing the current progress on transfer learning for classification, regression and clustering problems. In this survey, we discuss the relationship between transfer learning and other related machine learning techniques such as domain adaptation, multitask learning and sample selection bias, as well as covariate shift. We also explore some potential future issues in transfer learning research.
Regularized multitask learning
, 2004
"... This paper provides a foundation for multi–task learning using reproducing kernel Hilbert spaces of vector–valued functions. In this setting, the kernel is a matrix–valued function. Some explicit examples will be described which go beyond our earlier results in [7]. In particular, we characterize cl ..."
Abstract

Cited by 277 (2 self)
 Add to MetaCart
(Show Context)
This paper provides a foundation for multi–task learning using reproducing kernel Hilbert spaces of vector–valued functions. In this setting, the kernel is a matrix–valued function. Some explicit examples will be described which go beyond our earlier results in [7]. In particular, we characterize classes of matrix– valued kernels which are linear and are of the dot product or the translation invariant type. We discuss how these kernels can be used to model relations between the tasks and present linear multi–task learning algorithms. Finally, we present a novel proof of the representer theorem for a minimizer of a regularization functional which is based on the notion of minimal norm interpolation. 1
Learning Multiple Tasks with Kernel Methods
 Journal of Machine Learning Research
, 2005
"... Editor: John ShaweTaylor We study the problem of learning many related tasks simultaneously using kernel methods and regularization. The standard singletask kernel methods, such as support vector machines and regularization networks, are extended to the case of multitask learning. Our analysis sh ..."
Abstract

Cited by 251 (10 self)
 Add to MetaCart
(Show Context)
Editor: John ShaweTaylor We study the problem of learning many related tasks simultaneously using kernel methods and regularization. The standard singletask kernel methods, such as support vector machines and regularization networks, are extended to the case of multitask learning. Our analysis shows that the problem of estimating many task functions with regularization can be cast as a single task learning problem if a family of multitask kernel functions we define is used. These kernels model relations among the tasks and are derived from a novel form of regularizers. Specific kernels that can be used for multitask learning are provided and experimentally tested on two real data sets. In agreement with past empirical work on multitask learning, the experiments show that learning multiple related tasks simultaneously using the proposed approach can significantly outperform standard singletask learning particularly when there are many related tasks but few data per task.
Separating style and content with bilinear models
 NEURAL COMPUTATION
, 2000
"... PERCEPTUAL systems routinely separate content from style, classifying familiar words spoken in an unfamiliar accent, identifying a font or handwriting style across letters, or recognizing a familiar face or object seen under unfamiliar viewing conditions. Yet a general and tractable computational mo ..."
Abstract

Cited by 225 (3 self)
 Add to MetaCart
PERCEPTUAL systems routinely separate content from style, classifying familiar words spoken in an unfamiliar accent, identifying a font or handwriting style across letters, or recognizing a familiar face or object seen under unfamiliar viewing conditions. Yet a general and tractable computational model of this ability to untangle the underlying factors of perceptual observations remains elusive. Existing factor models are either insufficiently rich to capture the complex interactions of perceptually meaningful factors such as phoneme and speaker accent or letter and font, or do not allow efficient learning algorithms. Here we show how perceptual systems may learn to solve these crucial tasks using surprisingly simple bilinear models. We report promising results in three realistic perceptual domains: spoken vowel classification with a benchmark multispeaker database, extrapolation of fonts to unseen letters, and translation of faces to novel illuminants.
A Model of Inductive Bias Learning
 Journal of Artificial Intelligence Research
, 2000
"... A major problem in machine learning is that of inductive bias: how to choose a learner's hypothesis space so that it is large enough to contain a solution to the problem being learnt, yet small enough to ensure reliable generalization from reasonablysized training sets. Typically such bias is ..."
Abstract

Cited by 193 (0 self)
 Add to MetaCart
(Show Context)
A major problem in machine learning is that of inductive bias: how to choose a learner's hypothesis space so that it is large enough to contain a solution to the problem being learnt, yet small enough to ensure reliable generalization from reasonablysized training sets. Typically such bias is supplied by hand through the skill and insights of experts. In this paper a model for automatically learning bias is investigated. The central assumption of the model is that the learner is embedded within an environment of related learning tasks. Within such an environment the learner can sample from multiple tasks, and hence it can search for a hypothesis space that contains good solutions to many of the problems in the environment. Under certain restrictions on the set of all hypothesis spaces available to the learner, we show that a hypothesis space that performs well on a sufficiently large number of training tasks will also perform well when learning novel tasks in the same environment. Exp...
Multitask learning for classification with dirichlet process priors
 Journal of Machine Learning Research
, 2007
"... Multitask learning (MTL) is considered for logisticregression classifiers, based on a Dirichlet process (DP) formulation. A symmetric MTL (SMTL) formulation is considered in which classifiers for multiple tasks are learned jointly, with a variational Bayesian (VB) solution. We also consider an asy ..."
Abstract

Cited by 140 (12 self)
 Add to MetaCart
(Show Context)
Multitask learning (MTL) is considered for logisticregression classifiers, based on a Dirichlet process (DP) formulation. A symmetric MTL (SMTL) formulation is considered in which classifiers for multiple tasks are learned jointly, with a variational Bayesian (VB) solution. We also consider an asymmetric MTL (AMTL) formulation in which the posterior density function from the SMTL model parameters, from previous tasks, is used as a prior for a new task; this approach has the significant advantage of not requiring storage and use of all previous data from prior tasks. The AMTL formulation is solved with a simple Markov Chain Monte Carlo (MCMC) construction. Comparisons are also made to simpler approaches, such as singletask learning, pooling of data across tasks, and simplified approximations to DP. A comprehensive analysis of algorithm performance is addressed through consideration of two data sets that are matched to the MTL problem.
MultiTask Feature and Kernel Selection for SVMs
 Proc. of ICML 2004
, 2004
"... We compute a common feature selection or kernel selection con guration for multiple support vector machines (SVMs) trained on dierent yet interrelated datasets. The method is advantageous when multiple classi cation tasks and dierently labeled datasets exist over a common input space. Diere ..."
Abstract

Cited by 84 (3 self)
 Add to MetaCart
We compute a common feature selection or kernel selection con guration for multiple support vector machines (SVMs) trained on dierent yet interrelated datasets. The method is advantageous when multiple classi cation tasks and dierently labeled datasets exist over a common input space. Dierent datasets can mutually reinforce a common choice of representation or relevant features for their various classi ers. We derive a multitask representation learning approach using the maximum entropy discrimination formalism. The resulting convex algorithms maintain the global solution properties of support vector machines. However, in addition to multiple SVM classi cation /regression parameters they also jointly estimate an optimal subset of features or optimal combination of kernels. Experiments are shown on standardized datasets.
Domain adaptation problems: A DASVM classification technique and a circular validation strategy
 PAMI
"... ABSTRACT—This paper addresses pattern classification in the framework of domain adaptation by considering methods that solve problems in which training data are assumed to be available only for a source domain different (even if related) from the target domain of (unlabeled) test data. Two main nove ..."
Abstract

Cited by 54 (2 self)
 Add to MetaCart
(Show Context)
ABSTRACT—This paper addresses pattern classification in the framework of domain adaptation by considering methods that solve problems in which training data are assumed to be available only for a source domain different (even if related) from the target domain of (unlabeled) test data. Two main novel contributions are proposed: 1) a domain adaptation support vector machine (DASVM) technique which extends the formulation of support vector machines (SVMs) to the domain adaptation framework and 2) a circular indirect accuracy assessment strategy for validating the learning of domain adaptation classifiers when no true labels for the targetdomain instances are available. Experimental results, obtained on a series of twodimensional toy problems and on two real data sets related to brain computer interface and remote sensing applications, confirmed the effectiveness and the reliability of both the DASVM technique and the proposed circular validation strategy. Index Terms—Domain adaptation, transfer learning, semisupervised learning, support vector machines, accuracy assessment, validation strategy. Ç 1