Preference Learning

  title={Preference Learning},
  author={Johannes F{\"u}rnkranz and Eyke H{\"u}llermeier},
  booktitle={K{\"u}nstliche Intell.},
By combining practical relevance with novel types of prediction problems, the learning from/of preferences has recently received a lot of attention in the machine learning literature. Just as other types of complex learning tasks, preference learning deviates strongly from the standard problems of classification and regression. It is particularly challenging because it involves the prediction of complex structures, such as weak or partial order relations, rather than single values. This article… 
Learning Label Preferences: Ranking Error Versus Position Error
A key advantage of such a decomposition, namely the fact that the learner can be adapted to different loss functions by using different ranking procedures on the same underlying order relations, is elaborated on.
Semiparametric preference learning
A semiparametric preference learning model, abbreviated as SPPL, with the aim of combining the strengths of the parametric and nonparametric approaches is proposed, which is more powerful than previous models while keeping the computational complexity low.
Efficiently learning the preferences of people
This paper proposes an alternative for the standard criteria in active learning which actively chooses queries by making use of the available preference data from other subjects, the advantage of this alternative is the reduced computation costs and reduced time subjects are involved.
Predicting Partial Orders: Ranking with Abstention
A general approach to ranking with partial abstention is proposed as well as evaluation metrics for measuring the correctness and completeness of predictions, able to achieve a reasonable trade-off between these two criteria.
Editorial: Preference learning and ranking
The topic of preference learning and ranking has established itself as a new subfield of machine learning in recent years—a development that is witnessed by a continuously growing number of publications on this topic as well as the organization of dedicated events.
Interpretable preference learning: a game theoretic framework for large margin on-line feature and rule learning
In this work, game theory notions are injected into a preference learning framework and an algorithm is proposed to incrementally include new useful features into the hypothesis, leveraging on the natural analogy between features and rules.
Label ranking by learning pairwise preferences
SortNet: Learning to Rank by a Neural Preference Function
This paper presents a preference learning method, trained from examples to approximate the comparison function for a pair of objects, that can be embedded as the comparator into a classical sorting algorithm to provide a global ranking of a set of objects.
Learning Probabilistic CP-nets from Observations of Optimal Items
It is studied in this paper how Probabilistic Conditional Preference networks can be learnt, both in off-line and on-line settings.
Towards Preference-Based Reinforcement Learning
This paper proposes an alternative framework for reinforcement learning, in which qualitative reward signals can be directly used by the learner, and realizes a first simple instantiation of this framework that defines preferences based on utilities observed for trajectories.


Pairwise Preference Learning and Ranking
The main objective of this work is to investigate the trade-off between the quality of the induced ranking function and the computational complexity of the algorithm, both depending on the amount of preference information given for each example.
Supervised learning of preference relations
An approach is presented that performs a linear mapping from objects to utility values and thus guarantees transitivity and antisymmetry and is extended to nonlinear utility functions by using the potential function method, which allows to incorporate higher order correlations of features into the utility func tion at minimal computational costs.
Connectionist Learning of Expert Preferences by Comparison Training
A new training paradigm, called the "comparison paradigm," is introduced for tasks in which a network must learn to choose a preferred pattern from a set of n alternatives, based on examples of human
Learning to Order Things
An on-line algorithm for learning preference functions that is based on Freund and Schapire's "Hedge" algorithm is considered, and it is shown that the problem of finding the ordering that agrees best with a learned preference function is NP-complete.
Optimizing search engines using clickthrough data
The goal of this paper is to develop a method that utilizes clickthrough data for training, namely the query-log of the search engine in connection with the log of links the users clicked on in the presented ranking.
Constraint Classification: A New Approach to Multiclass Classification
This paper provides the first optimal, distribution independent bounds for many multiclass learning algorithms, including winner-take-all (WTA), and presents a learning algorithm that learns via a single linear classifier in high dimension.
Prospects for Preferences
  • J. Doyle
  • Economics, Psychology
    Comput. Intell.
  • 2004
This article examines prospects for theories and methods of preferences, both in the specific sense of the preferences of the ideal rational agents considered in economics and decision theory and in
Learning to order things Prospects for Preferences Pairwise preference learning and ranking
    FG Knowledge Engineering Hochschulstr. 10, 64289 Darmstadt Email:
    • FG Knowledge Engineering Hochschulstr. 10, 64289 Darmstadt Email: