← Back to all news
arXiv AI

Pairwise Difference Learning for Classification

The paper introduces Pairwise Difference Learning (PDL) for classification, extending a meta‑learning technique originally designed for regression. PDL learns a function that predicts the difference between outcomes of two instances; predictions for a new instance are obtained by averaging differences with all training examples. Experiments show that the resulting PDL classifier surpasses state‑of‑the‑art methods, and the authors release a user‑friendly Python implementation.

Related stories

arXiv AI
Oct 16

Efficient Pairwise Difference Learning: A Comparative Study of Encoding Strategies and Training Pair Selection

The paper evaluates how different encoding strategies and pair selection methods affect Pairwise Difference Learning (PDC) for classification. It compares four encoders—including a new triplet with absolute difference—and four pair selection schemes across almost 200 datasets using several base models. The study finds that the new encoder yields the best average F1 scores, that using only upper‑triangle pairs cuts training time by about 40% with little accuracy loss, and that no single configuration dominates across all datasets.

By Bernard Georges, Mohamed Karim Belaid, Manuel Rodrigues
benchmarks
More like this →
arXiv Machine Learning
Sep 24

Binary Classification from Coupled Pairwise Labels

The paper introduces SD-Pcomp learning, a binary classification framework that jointly utilizes Similarity/Dissimilarity (SD) labels and Pairwise Comparison (Pcomp) labels from instance pairs. It proposes an objective function that can be decomposed into either an SD estimator plus ordering information or a Pcomp estimator plus pair-type information, thereby integrating complementary relational cues. Experiments on eight datasets demonstrate that combining both label types improves classification accuracy and AUC compared to using either alone or a simple convex combination.

By Tomoya Tate, Kosuke Sugiyama, Masato Uchida
More like this →
arXiv Machine Learning
Sep 18

Alliance Beats Isolation: Unifying Heterogeneous Allied Datasets Improves Classifier Performance

The paper introduces a method for combining heterogeneous, allied datasets—datasets that share the same class labels but have disjoint objects and largely distinct feature spaces—into a single unified feature space. By applying matrix completion to this merged space, the authors create a unified dataset that enables knowledge transfer between the original datasets. Experiments across multiple dataset pairs and classifiers show that models trained on the unified representation consistently outperform those trained separately on each dataset.

By Girish Keshav Palshikar
More like this →
arXiv Machine Learning
Sep 11

Meta-Learning for Classifier Selection in Image Datasets: A Feature-Driven Framework for Accuracy Prediction

The paper introduces a meta‑learning framework that uses a rich set of dataset‑complexity meta‑features to predict the accuracy of different classifiers on image datasets, avoiding exhaustive training. By extracting features with autoencoders, pre‑trained networks, and dimensionality reduction, regression models estimate classifier accuracies, while clustering groups similar performers to simplify recommendations. Tested on 56 diverse image datasets, the method achieves over 86% ranking prediction accuracy, offering a scalable, interpretable solution for model selection and cost reduction.

By Zahra Nabizadeh_Shahre_Babak, Farzaneh Koohestani, Nader Karimi, Shahram Shirani, Shadrokh Samavi
More like this →