# Pairwise Difference Learning for Classification

arXiv: https://arxiv.org/abs/2406.20031 · HTML: https://mlsanity.com/paper/2406.20031/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 23 references that are in the map.
- First posted on arXiv 28 Jun 2024.

## Builds on (most cited first, 7 of 7)

- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [OpenML Benchmarking Suites](https://mlsanity.com/paper/1708.03731/) (2017)
- [Evaluation of a Tree-based Pipeline Optimization Tool for Automating Data Science](https://mlsanity.com/paper/1603.06212/) (2016)
- [Twin Neural Network Regression](https://mlsanity.com/paper/2012.14873/) (2020)
- [Twin Neural Network Regression is a Semi-Supervised Regression Algorithm](https://mlsanity.com/paper/2106.06124/) (2021)
- [Optimizing Data Shapley Interaction Calculation from O(2^n) to O(t n^2) for KNN models](https://mlsanity.com/paper/2304.01224/) (2023)

## Built on by (most cited first, 2 of 2)

- [Ranking-Based At-Risk Student Prediction Using Federated Learning and Differential Features](https://mlsanity.com/paper/2505.09287/) (2025)
- [Inverting Non-Injective Functions with Twin Neural Network Regression](https://mlsanity.com/paper/2601.05378/) (2026)

## Abstract (arXiv)

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.