TITLE

Bayesian multi-instance multi-label learning using Gaussian process prior

AUTHOR(S)
He, Jianjun; Gu, Hong; Wang, Zhelong
PUB. DATE
July 2012
SOURCE
Machine Learning;Jul2012, Vol. 88 Issue 1/2, p273
SOURCE TYPE
Academic Journal
DOC. TYPE
Article
ABSTRACT
Multi-instance multi-label learning (MIML) is a newly proposed framework, in which the multi-label problems are investigated by representing each sample with multiple feature vectors named instances. In this framework, the multi-label learning task becomes to learn a many-to-many relationship, and it also offers a possibility for explaining why a concerned sample has the certain class labels. The connections between instances and labels as well as the correlations among labels are equally crucial information for MIML. However, the existing MIML algorithms can rarely exploit them simultaneously. In this paper, a new MIML algorithm is proposed based on Gaussian process. The basic idea is to suppose a latent function with Gaussian process prior in the instance space for each label and infer the predictive probability of labels by integrating over uncertainties in these functions using the Bayesian approach, so that the connection between instances and every label can be exploited by defining a likelihood function and the correlations among labels can be identified by the covariance matrix of the latent functions. Moreover, since different relationships between instances and labels can be captured by defining different likelihood functions, the algorithm may be used to deal with the problems with various multi-instance assumptions. Experimental results on several benchmark data sets show that the proposed algorithm is valid and can achieve superior performance to the existing ones.
ACCESSION #
76517365

 

Related Articles

  • Large Margin Hierarchical Classification with Mutually Exclusive Class Membership. Wang, Huixin; Shen, Xiaotong; Pan, Wei // Journal of Machine Learning Research;Sep2011, Vol. 12 Issue 9, p2721 

    In hierarchical classification, class labels are structured, that is each label value corresponds to one non-root node in a tree, where the inter-class relationship for classification is specified by directed paths of the tree. In such a situation, the focus has been on how to leverage the...

  • Multiple instance learning via Gaussian processes. Kim, Minyoung; Torre, Fernando // Data Mining & Knowledge Discovery;Jul2014, Vol. 28 Issue 4, p1078 

    Multiple instance learning (MIL) is a binary classification problem with loosely supervised data where a class label is assigned only to a bag of instances indicating presence/absence of positive instances. In this paper we introduce a novel MIL algorithm using Gaussian processes (GP). The bag...

  • Differential Privacy for Functions and Functional Data. Hall, Rob; Rinaldo, Alessandro; Wasserman, Larry // Journal of Machine Learning Research;Jan2013, Vol. 14 Issue 1, p703 

    Differential privacy is a rigorous cryptographically-motivated characterization of data privacy which may be applied when releasing summaries of a database. Previous work has focused mainly on methods for which the output is a finite dimensional vector, or an element of some discrete set. We...

  • Focused multi-task learning in a Gaussian process framework. Leen, Gayle; Peltonen, Jaakko; Kaski, Samuel // Machine Learning;Oct2012, Vol. 89 Issue 1/2, p157 

    Multi-task learning, learning of a set of tasks together, can improve performance in the individual learning tasks. Gaussian process models have been applied to learning a set of tasks on different data sets, by constructing joint priors for functions underlying the tasks. In these previous...

  • Hierarchical Bayesian semiparametric procedures for logistic regression. HSU, JOHN S. J.; LEONARD, TOM // Biometrika;1997, Vol. 84 Issue 1, p85 

    A simple procedure is proposed for exact computation to smooth Bayesian estimates for logistic regression functions, when these are not constrained to lie on a fitted regression surface. Exact finite sample inferences and predictions are available, together with an exact residual analysis. The...

  • The application of a hierarchical Bayesian spatiotemporal model for forecasting the SAA trapped particle flux distribution. Suparta, Wayan; Gusrizal // Journal of Earth System Science;Aug2014, Vol. 123 Issue 6, p1287 

    We implement a hierarchical Bayesian spatiotemporal (HBST) model to forecast the daily trapped particle flux distribution over the South Atlantic Anomaly (SAA) region. The National Oceanic and Atmospheric Administration (NOAA)-15 data from 1-30 March 2008 with particle energies as >30 keV...

  • Statistical topic models for multi-label document classification. Rubin, Timothy; Chambers, America; Smyth, Padhraic; Steyvers, Mark // Machine Learning;Jul2012, Vol. 88 Issue 1/2, p157 

    Machine learning approaches to multi-label document classification have to date largely relied on discriminative modeling techniques such as support vector machines. A drawback of these approaches is that performance rapidly drops off as the total number of labels and the number of labels per...

  • Proactive Password Strength Analyzer Using Filters and Machine Learning Techniques.  // International Journal of Computer Applications;Sep2010, Vol. 7, p1 

    The article discusses the use of filters and machine learning techniques in proactive password strength analyzer. It tackles the significance of password authentication in organizations as well as the policies governing the creation and use of passwords. It mentions the use of support vector...

  • Predicting complications of percutaneous coronary intervention using a novel support vector method. Lee, Gyemin; Gurm, Hitinder S.; Syed, Zeeshan // Journal of the American Medical Informatics Association;Jul2013, Vol. 20 Issue 4, p778 

    Objective To explore the feasibility of a novel approach using an augmented one-class learning algorithm to model in-laboratory complications of percutaneous coronary intervention (PCI). Materials and methods Data from the Blue Cross Blue Shield of Michigan Cardiovascular Consortium (BMC2)...

Share

Read the Article

Courtesy of THE LIBRARY OF VIRGINIA

Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics