A flexible generative model for preference aggregation

Many areas of study, such as information retrieval, collaborative filtering, and social choice face the preference aggregation problem, in which multiple preferences over objects must be combined into a consensus ranking. Preferences over items can be expressed in a variety of forms, which makes the aggregation problem difficult. In this work we formulate a flexible probabilistic model over pairwise comparisons that can accommodate all these forms. Inference in the model is very fast, making it applicable to problems with hundreds of thousands of preferences. Experiments on benchmark datasets demonstrate superior performance to existing methods

[1]  Ronald Fagin,et al.  Efficient similarity search and classification via rank aggregation , 2003, SIGMOD '03.

[2]  Jeff A. Bilmes,et al.  Consensus ranking under the exponential model , 2007, UAI.

[3]  R. Plackett.  The Analysis of Permutations , 1975 .

[4]  Jaana Kekäläinen,et al.  IR evaluation methods for retrieving highly relevant documents , 2000, SIGIR '00.

[5]  Yuan Yao,et al.  Statistical ranking and combinatorial Hodge theory , 2008, Math. Program..

[6]  Craig Boutilier,et al.  Learning Mallows Models with Pairwise Preferences , 2011, ICML.

[7]  David F. Gleich,et al.  Rank aggregation via nuclear norm minimization , 2011, KDD.

[8]  John Guiver,et al.  Bayesian inference for Plackett-Luce ranking models , 2009, ICML '09.

[9]  Javed A. Aslam,et al.  Models for metasearch , 2001, SIGIR '01.

[10]  C. L. Mallows.  NON-NULL RANKING MODELS. I , 1957 .

[11]  R. Luce,et al.  Individual Choice Behavior: A Theoretical Analysis. , 1960 .

[12]  Dan Roth,et al.  Unsupervised rank aggregation with distance-based models , 2008, ICML '08.

[13]  Ruslan Salakhutdinov,et al.  Probabilistic Matrix Factorization , 2007, NIPS.

[14]  David Mease,et al.  A Penalized Maximum Likelihood Approach for the Ranking of College Football Teams Independent of Victory Margins , 2003 .

[15]  A. Elo.  The rating of chessplayers, past and present , 1978 .

[16]  H. A. David,et al.  The method of paired comparisons , 1966 .

[17]  R. Duncan Luce,et al.  Individual Choice Behavior: A Theoretical Analysis , 1979 .

[18]  Ruslan Salakhutdinov,et al.  Bayesian probabilistic matrix factorization using Markov chain Monte Carlo , 2008, ICML '08.

[19]  R. A. Bradley,et al.  RANK ANALYSIS OF INCOMPLETE BLOCK DESIGNS , 1952 .

[20]  Tao Qin,et al.  Supervised rank aggregation , 2007, WWW '07.

[21]  Tao Qin,et al.  A New Probabilistic Model for Rank Aggregation , 2010, NIPS.

[22]  Tom Minka,et al.  TrueSkill Through Time: Revisiting the History of Chess , 2007, NIPS.

[23]  Alexander Dekhtyar,et al.  Information Retrieval , 2018, Lecture Notes in Computer Science.

[24]  R. A. Bradley,et al.  Rank Analysis of Incomplete Block Designs: I. The Method of Paired Comparisons , 1952 .

[25]  Richard S. Zemel,et al.  Unsupervised Learning with Non-Ignorable Missing Data , 2005, AISTATS.

[26]  L. Thurstone.  The method of paired comparisons for social values , 1927 .

[27]  Gregory N. Hullender,et al.  Learning to rank using gradient descent , 2005, ICML.

[28]  John D. Lafferty,et al.  Cranking: Combining Rankings Using Conditional Probability Models on Permutations , 2002, ICML.

[29]  Tao Qin,et al.  LETOR: Benchmark Dataset for Research on Learning to Rank for Information Retrieval , 2007 .