Pairwise Difference Learning for Classification
This work addresses classification tasks for machine learning practitioners by offering a novel meta-learning approach, though it is incremental as it builds on an existing regression method.
The paper extends pairwise difference learning (PDL) from regression to classification by proposing a meta-learning technique that transforms the training data into paired instances to predict outcome differences, and it shows that the PDL classifier outperforms state-of-the-art methods in a large-scale empirical study.
Pairwise difference learning (PDL) has recently been introduced as a new meta-learning technique for regression. Instead of learning a mapping from instances to outcomes in the standard way, the key idea is to learn a function that takes two instances as input and predicts the difference between the respective outcomes. Given a function of this kind, predictions for a query instance are derived from every training example and then averaged. This paper extends PDL toward the task of classification and proposes a meta-learning technique for inducing a PDL classifier by solving a suitably defined (binary) classification problem on a paired version of the original training data. We analyze the performance of the PDL classifier in a large-scale empirical study and find that it outperforms state-of-the-art methods in terms of prediction performance. Last but not least, we provide an easy-to-use and publicly available implementation of PDL in a Python package.