Local Explanation of Dimensionality Reduction

2022-04-29 · Avraam Bardos, Ioannis Mollas, Nick Bassiliades, Grigorios Tsoumakas

Dimensionality reduction (DR) is a popular method for preparing and analyzing high-dimensional data. Reduced data representations are less computationally intensive and easier to manage and visualize, while retaining a significant percentage of their original information. Aside from these advantages, these reduced representations can be difficult or impossible to interpret in most circumstances, especially when the DR approach does not provide further information about which features of the original space led to their construction. This problem is addressed by Interpretable Machine Learning, a subfield of Explainable Artificial Intelligence that addresses the opacity of machine learning models. However, current research on Interpretable Machine Learning has been focused on supervised tasks, leaving unsupervised tasks like Dimensionality Reduction unexplored. In this paper, we introduce LXDR, a technique capable of providing local interpretations of the output of DR techniques. Experiment results and two LXDR use case examples are presented to evaluate its usefulness.

📄 PDF Abstract BibTeX arXiv:2204.14012

Code (1)

avrambardas/interpretable-unsupervised-learning 공식 구현 pytorch

Tasks

BIG-bench Machine Learning Dimensionality ReductionExplainable artificial intelligenceInterpretable Machine Learning

"Why Here and Not There?" -- Diverse Contrasting Explanations of Dimensionality Reduction

2022-06-15 · André Artelt, Alexander Schulz, Barbara Hammer

Dimensionality reduction is a popular preprocessing and a widely used tool in data mining. Transparency, which is usually achieved by means of explanations, is nowadays a widely accepted and crucial requirement of machin…

Data Visualization Dimensionality Reduction Recommendation Systems

SLISEMAP: Supervised dimensionality reduction through local explanations

2022-01-12 · Anton Björklund, Jarmo Mäkelä, Kai Puolamäki

Existing methods for explaining black box learning models often focus on building local explanations of model behaviour for a particular data item. It is possible to create global explanations for all data items, but the…

Classification Dimensionality Reduction Explainable Models GPU+1

SHAPCA: Consistent and Interpretable Explanations for Machine Learning Models on Spectroscopy Data

2026-03-19 · Mingxing Zhang, Nicola Rossberg, Simone Innocente, Katarzyna Komolibus 외 arxiv

In recent years, machine learning models have been increasingly applied to spectroscopic datasets for chemical and biomedical analysis. For their successful adoption, particularly in clinical and safety-critical settings…

Dimensionality Reduction Feature Importance

A Local Similarity-Preserving Framework for Nonlinear Dimensionality Reduction with Neural Networks

2021-03-10 · Xiang Wang, Xiaoyong Li, Junxing Zhu, Zichen Xu 외

Real-world data usually have high dimensionality and it is important to mitigate the curse of dimensionality. High-dimensional data are usually in a coherent structure and make the data in relatively small true degrees o…

Clustering Dimensionality Reduction Representation Learning

Explainability-Driven Dimensionality Reduction for Hyperspectral Imaging

2025-09-02 · Salma Haidar, José Oramas arxiv

Hyperspectral imaging (HSI) provides rich spectral information for precise material classification and analysis; however, its high dimensionality introduces a computational burden and redundancy, making dimensionality re…

Dimensionality Reduction