# ParaDime: A Framework for Parametric Dimensionality Reduction

arXiv: https://arxiv.org/abs/2210.04582 · HTML: https://mlsanity.com/paper/2210.04582/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 69 references that are in the map.
- First posted on arXiv 10 Oct 2022.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://mlsanity.com/paper/1603.04467/) (2016)
- [Learning Fine-grained Image Similarity with Deep Ranking](https://mlsanity.com/paper/1404.4661/) (2014)
- [Parametric UMAP embeddings for representation and semi-supervised learning](https://mlsanity.com/paper/2009.12981/) (2020)
- [Visualizing Large-scale and High-dimensional Data](https://mlsanity.com/paper/1602.00370/) (2016)
- [Attraction-Repulsion Spectrum in Neighbor Embeddings](https://mlsanity.com/paper/2007.08902/) (2020)
- [On UMAP's true loss function](https://mlsanity.com/paper/2103.14608/) (2021)
- [From t-SNE to UMAP with contrastive learning](https://mlsanity.com/paper/2206.01816/) (2022)
- [Minimum-Distortion Embedding](https://mlsanity.com/paper/2103.02559/) (2021)
- [Neo: Generalizing Confusion Matrix Visualization to Hierarchical and Multi-Output Labels](https://mlsanity.com/paper/2110.12536/) (2021)
- [Projective Latent Interventions for Understanding and Fine-tuning Classifiers](https://mlsanity.com/paper/2006.12902/) (2020)
- [Encodable: Configurable Grammar for Visualization Components](https://mlsanity.com/paper/2009.00722/) (2020)

## Built on by (most cited first, 4 of 4)

- [Evaluating Autoencoders for Parametric and Invertible Multidimensional Projections](https://mlsanity.com/paper/2504.16831/) (2025)
- [Adversarial Attacks on Machine Learning-Aided Visualizations](https://mlsanity.com/paper/2409.02485/) (2024)
- [Out-of-Core Dimensionality Reduction for Large Data via Out-of-Sample Extensions](https://mlsanity.com/paper/2408.04129/) (2024)
- [Local Neighborhood Instability in Parametric Projections: Quantitative and Visual Analysis](https://mlsanity.com/paper/2604.21617/) (2026)

## Abstract (arXiv)

ParaDime is a framework for parametric dimensionality reduction (DR). In parametric DR, neural networks are trained to embed high-dimensional data items in a low-dimensional space while minimizing an objective function. ParaDime builds on the idea that the objective functions of several modern DR techniques result from transformed inter-item relationships. It provides a common interface for specifying these relations and transformations and for defining how they are used within the losses that govern the training process. Through this interface, ParaDime unifies parametric versions of DR techniques such as metric MDS, t-SNE, and UMAP. It allows users to fully customize all aspects of the DR process. We show how this ease of customization makes ParaDime suitable for experimenting with interesting techniques such as hybrid classification/embedding models and supervised DR. This way, ParaDime opens up new possibilities for visualizing high-dimensional data.