dlordinal: a Python package for deep ordinal classification

2024-07-24

Neurocomputing

AI Summary

Ordinal classification lacks dedicated, unified tooling in deep learning frameworks. Method: This paper introduces and open-sources the first PyTorch-native library specifically designed for ordinal classification. It systematically integrates state-of-the-art ordinal-constrained modeling techniques—including ordinal-aware loss functions (e.g., OrdinalCE, Soft-Ordinal), cumulative link output layers, ordinal-aware dropout, and soft-labeling strategies—and provides built-in ordinal-specific metrics (e.g., MAE, Kendall Tau). Contribution/Results: The library establishes the first end-to-end, scalable, and modular ordinal classification toolkit, filling a critical gap in mainstream deep learning ecosystems. It reproduces SOTA performance across multiple standard benchmarks, significantly improving modeling of label-order structure. Designed for both rapid research prototyping and industrial deployment, the codebase is released under the BSD-3-Clause license.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

dlordinal is a new Python library that unifies many recent deep ordinal classification methodologies available in the literature. Developed using PyTorch as underlying framework, it implements the top performing state-of-the-art deep learning techniques for ordinal classification problems. Ordinal approaches are designed to leverage the ordering information present in the target variable. Specifically, it includes loss functions, various output layers, dropout techniques, soft labelling methodologies, and other classification strategies, all of which are appropriately designed to incorporate the ordinal information. Furthermore, as the performance metrics to assess novel proposals in ordinal classification depend on the distance between target and predicted classes in the ordinal scale, suitable ordinal evaluation metrics are also included. dlordinal is distributed under the BSD-3-Clause license and is available at https://github.com/ayrna/dlordinal.

Problem

• Ordinal Classification
• Deep Learning
• Python Toolkit

Innovation

• Deep Learning Ordinal Classification
• PyTorch Framework
• Customized Evaluation Method