Results 1  10
of
92
Learning to rank: from pairwise approach to listwise approach
 In Proc. ICML’07
, 2007
"... The paper is concerned with learning to rank, which is to construct a model or a function for ranking objects. Learning to rank is useful for document retrieval, collaborative filtering, and many other applications. Several methods for learning to rank have been proposed, which take object pairs as ..."
Abstract

Cited by 239 (29 self)
 Add to MetaCart
The paper is concerned with learning to rank, which is to construct a model or a function for ranking objects. Learning to rank is useful for document retrieval, collaborative filtering, and many other applications. Several methods for learning to rank have been proposed, which take object pairs as ‘instances ’ in learning. We refer to them as the pairwise approach in this paper. Although the pairwise approach offers advantages, it ignores the fact that ranking is a prediction task on list of objects. The paper postulates that learning to rank should adopt the listwise approach in which lists of objects are used as ‘instances ’ in learning. The paper proposes a new probabilistic method for the approach. Specifically it introduces two probability models, respectively referred to as permutation probability and top one probability, to define a listwise loss function for learning. Neural Network and Gradient Descent are then employed as model and algorithm in the learning method. Experimental results on information retrieval show that the proposed listwise approach performs better than the pairwise approach. Microsoft technique report. A short version of this work is published
Learning Mallows Models with Pairwise Preferences
"... Learning preference distributions is a key problem in many areas (e.g., recommender systems, IR, social choice). However, many existing methods require restrictive data models for evidence about user preferences. We relax these restrictions by considering as data arbitrary pairwise comparisons—the f ..."
Abstract

Cited by 74 (9 self)
 Add to MetaCart
(Show Context)
Learning preference distributions is a key problem in many areas (e.g., recommender systems, IR, social choice). However, many existing methods require restrictive data models for evidence about user preferences. We relax these restrictions by considering as data arbitrary pairwise comparisons—the fundamental building blocks of ordinal rankings. We develop the first algorithms for learning Mallows models (and mixtures) with pairwise comparisons. At the heart is a new algorithm, the generalized repeated insertion model (GRIM), for sampling from arbitrary ranking distributions. We develop approximate samplers that are exact for many important special cases—and have provable bounds with pairwise evidence—and derive algorithms for evaluating loglikelihood, learning Mallows mixtures, and nonparametric estimation. Experiments on large, realworld datasets show the effectiveness of our approach. 1.
MM algorithms for generalized BradleyTerry models
 The Annals of Statistics
, 2004
"... The Bradley–Terry model for paired comparisons is a simple and muchstudied means to describe the probabilities of the possible outcomes when individuals are judged against one another in pairs. Among the many studies of the model in the past 75 years, numerous authors have generalized it in several ..."
Abstract

Cited by 67 (2 self)
 Add to MetaCart
The Bradley–Terry model for paired comparisons is a simple and muchstudied means to describe the probabilities of the possible outcomes when individuals are judged against one another in pairs. Among the many studies of the model in the past 75 years, numerous authors have generalized it in several directions, sometimes providing iterative algorithms for obtaining maximum likelihood estimates for the generalizations. Building on a theory of algorithms known by the initials MM, for minorization–maximization, this paper presents a powerful technique for producing iterative maximum likelihood estimation algorithms for a wide class of generalizations of the Bradley–Terry model. While algorithms for problems of this type have tended to be custombuilt in the literature, the techniques in this paper enable their mass production. Simple conditions are stated that guarantee that each algorithm described will produce a sequence that converges to the unique maximum likelihood estimator. Several of the algorithms and convergence results herein are new. 1. Introduction. In
Multilevel logistic regression for polytomous data and rankings
, 2003
"... We propose a unifying framework for multilevel modeling of polytomous data and rankings, accommodating dependence induced by factor and/or random coefficient structures at different levels. The framework subsumes a wide range of models proposed in disparate methodological literatures. Partial and ti ..."
Abstract

Cited by 41 (12 self)
 Add to MetaCart
(Show Context)
We propose a unifying framework for multilevel modeling of polytomous data and rankings, accommodating dependence induced by factor and/or random coefficient structures at different levels. The framework subsumes a wide range of models proposed in disparate methodological literatures. Partial and tied rankings, alternative specific explanatory variables and alternative sets varying across units are handled. The problem of identification is addressed. We develop an estimation and prediction methodology for the model framework which is implemented in the generally available gllamm software. The methodology is applied to party choice and rankings from the 1987–1992 panel of the British Election Study. Three levels are considered: elections, voters and constituencies. Key words: multilevel models, generalized linear latent and mixed models, factor models, random coefficient models, polytomous data, rankings, first choice, discrete choice, permutations, nominal data, gllamm.
Bayesian inference for PlackettLuce ranking models
"... This paper gives an efficient Bayesian method for inferring the parameters of a PlackettLuce ranking model. Such models are parameterised distributions over rankings of a finite set of objects, and have typically been studied and applied within the psychometric, sociometric and econometric literatu ..."
Abstract

Cited by 32 (0 self)
 Add to MetaCart
(Show Context)
This paper gives an efficient Bayesian method for inferring the parameters of a PlackettLuce ranking model. Such models are parameterised distributions over rankings of a finite set of objects, and have typically been studied and applied within the psychometric, sociometric and econometric literature. The inference scheme is an application of Power EP (expectation propagation). The scheme is robust and can be readily applied to large scale data sets. The inference algorithm extends to variations of the basic PlackettLuce model, including partial rankings. We show a number of advantages of the EP approach over the traditional maximum likelihood method. We apply the method to aggregate rankings of NASCAR racing drivers over the 2002 season, and also to rankings of movie genres. 1.
Pairwise Ranking Aggregation in a Crowdsourced Setting
"... Inferring rankings over elements of a set of objects, such as documents or images, is a key learning problem for such important applications as Web search and recommender systems. Crowdsourcing services provide an inexpensive and efficient means to acquire preferences over objects via labeling by se ..."
Abstract

Cited by 27 (1 self)
 Add to MetaCart
(Show Context)
Inferring rankings over elements of a set of objects, such as documents or images, is a key learning problem for such important applications as Web search and recommender systems. Crowdsourcing services provide an inexpensive and efficient means to acquire preferences over objects via labeling by sets of annotators. We propose a new model to predict a goldstandard ranking that hinges on combining pairwise comparisons via crowdsourcing. In contrast to traditional ranking aggregation methods, the approach learns about and folds into consideration the quality of contributions of each annotator. In addition, we minimize the cost of assessment by introducing a generalization of the traditional active learning scenario to jointly select the annotator and pair to assess while taking into account the annotator quality, the uncertainty over ordering of the pair, and the current model uncertainty. We formalize this as an active learning strategy that incorporates an explorationexploitation tradeoff and implement it using an efficient online Bayesian updating scheme. Using simulated and realworld data, we demonstrate that the active learning strategy achieves significant reductions in labeling cost while maintaining accuracy.
Matrix estimation by universal singular value thresholding
, 2012
"... Abstract. Consider the problem of estimating the entries of a large matrix, when the observed entries are noisy versions of a small random fraction of the original entries. This problem has received widespread attention in recent times, especially after the pioneering works of Emmanuel Candès and ..."
Abstract

Cited by 25 (0 self)
 Add to MetaCart
(Show Context)
Abstract. Consider the problem of estimating the entries of a large matrix, when the observed entries are noisy versions of a small random fraction of the original entries. This problem has received widespread attention in recent times, especially after the pioneering works of Emmanuel Candès and collaborators. This paper introduces a simple estimation procedure, called Universal Singular Value Thresholding (USVT), that works for any matrix that has ‘a little bit of structure’. Surprisingly, this simple estimator achieves the minimax error rate up to a constant factor. The method is applied to solve problems related to low rank matrix estimation, blockmodels, distance matrix completion, latent space models, positive definite matrix completion, graphon estimation, and generalized Bradley–Terry models for pairwise comparison. 1.
A New Probabilistic Model for Rank Aggregation
"... This paper is concerned with rank aggregation, which aims to combine multiple input rankings to get a better ranking. A popular approach to rank aggregation is based on probabilistic models on permutations, e.g., the Luce model and the Mallows model. However, these models have their limitations in e ..."
Abstract

Cited by 22 (0 self)
 Add to MetaCart
(Show Context)
This paper is concerned with rank aggregation, which aims to combine multiple input rankings to get a better ranking. A popular approach to rank aggregation is based on probabilistic models on permutations, e.g., the Luce model and the Mallows model. However, these models have their limitations in either poor expressiveness or high computational complexity. To avoid these limitations, in this paper, we propose a new model, which is defined with a cosetpermutation distance, and models the generation of a permutation as a stagewise process. We refer to the new model as cosetpermutation distance based stagewise (CPS) model. The CPS model has rich expressiveness and can therefore be used in versatile applications, because many different permutation distances can be used to induce the cosetpermutation distance. The complexity of the CPS model is low because of the stagewise decomposition of the permutation probability and the efficient computation of most cosetpermutation distances. We apply the CPS model to supervised rank aggregation, derive the learning and inference algorithms, and empirically study their effectiveness and efficiency. Experiments on public datasets show that the derived algorithms based on the CPS model can achieve stateoftheart ranking accuracy, and are much more efficient than previous algorithms. 1
Random Utility Theory for Social Choice
"... Random utility theory models an agent’s preferences on alternatives by drawing a realvalued score on each alternative (typically independently) from a parameterized distribution, and then ranking the alternatives according to scores. A special case that has received significant attention is the Pla ..."
Abstract

Cited by 21 (10 self)
 Add to MetaCart
(Show Context)
Random utility theory models an agent’s preferences on alternatives by drawing a realvalued score on each alternative (typically independently) from a parameterized distribution, and then ranking the alternatives according to scores. A special case that has received significant attention is the PlackettLuce model, for which fast inference methods for maximum likelihood estimators are available. This paper develops conditions on general random utility models that enable fast inference within a Bayesian framework through MCEM, providing concave loglikelihood functions and bounded sets of global maxima solutions. Results on both realworld and simulated data provide support for the scalability of the approach and capability for model selection among general random utility models including PlackettLuce. 1
Breaking the Barriers: High Performance Security for High Performance Computing
 Proc. Workshop on New security paradigms
, 2002
"... This paper attempts to reconcile the high performance community's requirement of high performance with the need for security, and reconcile some accepted security approaches with the performance constraints of highperformance networks. We propose a new paradigm and challenge existing practice. ..."
Abstract

Cited by 21 (0 self)
 Add to MetaCart
(Show Context)
This paper attempts to reconcile the high performance community's requirement of high performance with the need for security, and reconcile some accepted security approaches with the performance constraints of highperformance networks. We propose a new paradigm and challenge existing practice. The new paradigm is that not all domains need longterm forward data confidentiality. In particular, we take a fresh look at security for the highperformance domain, focusing particularly on componentbased applications. We discuss the security and performance requirements of this domain in order to elucidate both the constraints and opportunities. We challenge the existing practice of highperformance networks sending communication in plaintext. We propose a security mechanism and provide metrics for analyzing both the security and performance costs.