Deep Architectures for Learning Context-dependent Ranking Functions

TL;DR

This paper introduces neural network-based methods for learning context-dependent ranking functions, addressing the limitation of traditional scoring approaches that ignore how context influences object utility.

Contribution

It formalizes the problem of context-dependent ranking and proposes two neural network architectures to model this complex dependency, evaluated on benchmark tasks.

Findings

Neural network models effectively capture context effects in ranking.

Proposed approaches outperform traditional scoring methods on benchmarks.

Context-aware ranking improves prediction accuracy.

Abstract

Object ranking is an important problem in the realm of preference learning. On the basis of training data in the form of a set of rankings of objects, which are typically represented as feature vectors, the goal is to learn a ranking function that predicts a linear order of any new set of objects. Current approaches commonly focus on ranking by scoring, i.e., on learning an underlying latent utility function that seeks to capture the inherent utility of each object. These approaches, however, are not able to take possible effects of context-dependence into account, where context-dependence means that the utility or usefulness of an object may also depend on what other objects are available as alternatives. In this paper, we formalize the problem of context-dependent ranking and present two general approaches based on two natural representations of context-dependent ranking functions. Both approaches are instantiated by means of appropriate neural network architectures, which are evaluated on suitable benchmark task.