Comprehensive review of dimensionality reduction algorithms: challenges, limitations, and innovative solutions
Dimensionality reduction (DR) simplifies complex data from genomics, imaging, sensors, and language into interpretable forms that support visualization, clustering, and modeling. Yet widely used methods like principal component analysis, t-distributed stochastic neighbor embedding, uniform manifold...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2025-07-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-3025.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850115045827018752 |
|---|---|
| author | Aasim Ayaz Wani |
| author_facet | Aasim Ayaz Wani |
| author_sort | Aasim Ayaz Wani |
| collection | DOAJ |
| description | Dimensionality reduction (DR) simplifies complex data from genomics, imaging, sensors, and language into interpretable forms that support visualization, clustering, and modeling. Yet widely used methods like principal component analysis, t-distributed stochastic neighbor embedding, uniform manifold approximation and projection, and autoencoders are often applied as “black boxes,” neglecting interpretability, fairness, stability, and privacy. This review introduces a unified classification—linear, nonlinear, hybrid, and ensemble approaches—and assesses them against eight core challenges: dimensionality selection, overfitting, instability, noise sensitivity, bias, scalability, privacy risks, and ethical compliance. We outline solutions such as intrinsic dimensionality estimation, robust neighborhood graphs, fairness-aware embeddings, scalable algorithms, and automated tuning. Drawing on case studies from bioinformatics, vision, language, and Internet of Things analytics, we offer a practical roadmap for deploying dimensionality reduction methods that are scalable, interpretable, and ethically sound—advancing responsible artificial intelligence in high-stakes applications. |
| format | Article |
| id | doaj-art-347a6b00cb5e4b5ea07c7381502df4f3 |
| institution | OA Journals |
| issn | 2376-5992 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj-art-347a6b00cb5e4b5ea07c7381502df4f32025-08-20T02:36:41ZengPeerJ Inc.PeerJ Computer Science2376-59922025-07-0111e302510.7717/peerj-cs.3025Comprehensive review of dimensionality reduction algorithms: challenges, limitations, and innovative solutionsAasim Ayaz WaniDimensionality reduction (DR) simplifies complex data from genomics, imaging, sensors, and language into interpretable forms that support visualization, clustering, and modeling. Yet widely used methods like principal component analysis, t-distributed stochastic neighbor embedding, uniform manifold approximation and projection, and autoencoders are often applied as “black boxes,” neglecting interpretability, fairness, stability, and privacy. This review introduces a unified classification—linear, nonlinear, hybrid, and ensemble approaches—and assesses them against eight core challenges: dimensionality selection, overfitting, instability, noise sensitivity, bias, scalability, privacy risks, and ethical compliance. We outline solutions such as intrinsic dimensionality estimation, robust neighborhood graphs, fairness-aware embeddings, scalable algorithms, and automated tuning. Drawing on case studies from bioinformatics, vision, language, and Internet of Things analytics, we offer a practical roadmap for deploying dimensionality reduction methods that are scalable, interpretable, and ethically sound—advancing responsible artificial intelligence in high-stakes applications.https://peerj.com/articles/cs-3025.pdfDimensionality reduction (DR)Principal component analysis (PCA)t-distributed stochastic neighbor embedding (t-SNE)Uniform manifold approximation and projection (UMAP)AutoencodersManifold learning |
| spellingShingle | Aasim Ayaz Wani Comprehensive review of dimensionality reduction algorithms: challenges, limitations, and innovative solutions PeerJ Computer Science Dimensionality reduction (DR) Principal component analysis (PCA) t-distributed stochastic neighbor embedding (t-SNE) Uniform manifold approximation and projection (UMAP) Autoencoders Manifold learning |
| title | Comprehensive review of dimensionality reduction algorithms: challenges, limitations, and innovative solutions |
| title_full | Comprehensive review of dimensionality reduction algorithms: challenges, limitations, and innovative solutions |
| title_fullStr | Comprehensive review of dimensionality reduction algorithms: challenges, limitations, and innovative solutions |
| title_full_unstemmed | Comprehensive review of dimensionality reduction algorithms: challenges, limitations, and innovative solutions |
| title_short | Comprehensive review of dimensionality reduction algorithms: challenges, limitations, and innovative solutions |
| title_sort | comprehensive review of dimensionality reduction algorithms challenges limitations and innovative solutions |
| topic | Dimensionality reduction (DR) Principal component analysis (PCA) t-distributed stochastic neighbor embedding (t-SNE) Uniform manifold approximation and projection (UMAP) Autoencoders Manifold learning |
| url | https://peerj.com/articles/cs-3025.pdf |
| work_keys_str_mv | AT aasimayazwani comprehensivereviewofdimensionalityreductionalgorithmschallengeslimitationsandinnovativesolutions |