Simultaneous Preference and Metric Learning from Paired Comparisons
share
A popular model of preference in the context of recommendation systems is the so-called ideal point model. In this model, a user is represented as a vector 𝐮 together with a collection of items 𝐱_1, …, 𝐱_𝐍 in a common low-dimensional space. The vector 𝐮 represents the user's "ideal point," or the ideal combination of features that represents a hypothesized most preferred item. The underlying assumption in this model is that a smaller distance between 𝐮 and an item 𝐱_𝐣 indicates a stronger preference for 𝐱_𝐣. In the vast majority of the existing work on learning ideal point models, the underlying distance has been assumed to be Euclidean. However, this eliminates any possibility of interactions between features and a user's underlying preferences. In this paper, we consider the problem of learning an ideal point representation of a user's preferences when the distance metric is an unknown Mahalanobis metric. Specifically, we present a novel approach to estimate the user's ideal point 𝐮 and the Mahalanobis metric from paired comparisons of the form "item 𝐱_𝐢 is preferred to item 𝐱_𝐣." This can be viewed as a special case of a more general metric learning problem where the location of some points are unknown a priori. We conduct extensive experiments on synthetic and real-world datasets to exhibit the effectiveness of our algorithm.
READ FULL TEXT