# Emblaze: Illuminating Machine Learning Representations through Interactive Comparison of Embedding Spaces

arXiv: https://arxiv.org/abs/2202.02641 · HTML: https://mlsanity.com/paper/2202.02641/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 52 references that are in the map.
- First posted on arXiv 5 Feb 2022.

## Builds on (most cited first, 14 of 14)

- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change](https://mlsanity.com/paper/1605.09096/) (2016)
- [Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers](https://mlsanity.com/paper/1801.06889/) (2018)
- [Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases](https://mlsanity.com/paper/2010.15052/) (2020)
- [Statistically Significant Detection of Linguistic Change](https://mlsanity.com/paper/1411.3315/) (2014)
- [Embedding Projector: Interactive Visualization and Interpretation of Embeddings](https://mlsanity.com/paper/1611.05469/) (2016)
- [Embedding Comparator: Visualizing Differences in Global Structure and Local Neighborhoods via Small Multiples](https://mlsanity.com/paper/1912.04853/) (2019)
- [EmbeddingVis: A Visual Analytics Approach to Comparative Network Embedding Inspection](https://mlsanity.com/paper/1808.09074/) (2018)
- [embComp: Visual Interactive Comparison of Vector Embeddings](https://mlsanity.com/paper/1911.01542/) (2019)
- [Interactive Dimensionality Reduction for Comparative Analysis](https://mlsanity.com/paper/2106.15481/) (2021)
- [Comparative Analysis of Word Embeddings for Capturing Word Similarities](https://mlsanity.com/paper/2005.03812/) (2020)
- [LAMVI-2: A Visual Tool for Comparing and Tuning Word Embedding Models](https://mlsanity.com/paper/1810.11367/) (2018)
- [TextEssence: A Tool for Interactive Analysis of Semantic Shifts Between Corpora](https://mlsanity.com/paper/2103.11029/) (2021)

## Built on by (most cited first, 16 of 16)

- [AttentionViz: A Global View of Transformer Attention](https://mlsanity.com/paper/2305.03210/) (2023)
- [WizMap: Scalable Interactive Visualization for Exploring Large Machine Learning Embeddings](https://mlsanity.com/paper/2306.09328/) (2023)
- [Visual Comparison of Language Model Adaptation](https://mlsanity.com/paper/2208.08176/) (2022)
- [A call for embodied AI](https://mlsanity.com/paper/2402.03824/) (2024)
- [Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships](https://mlsanity.com/paper/2407.12543/) (2024)
- [VideoMap: Supporting Video Editing Exploration, Brainstorming, and Prototyping in the Latent Space](https://mlsanity.com/paper/2211.12492/) (2022)
- [A Large-Scale Sensitivity Analysis on Latent Embeddings and Dimensionality Reductions for Text Spatializations](https://mlsanity.com/paper/2407.17876/) (2024)
- [Compress and Compare: Interactively Evaluating Efficiency and Behavior Across ML Model Compression Experiments](https://mlsanity.com/paper/2408.03274/) (2024)
- [Explainable Mapper: Charting LLM Embedding Spaces Using Perturbation-Based Explanation and Verification Agents](https://mlsanity.com/paper/2507.18607/) (2025)
- [SuperNOVA: Design Strategies and Opportunities for Interactive Visualization in Computational Notebooks](https://mlsanity.com/paper/2305.03039/) (2023)
- [Latent Space Explorer: Visual Analytics for Multimodal Latent Space Exploration](https://mlsanity.com/paper/2312.00857/) (2023)
- [k* Distribution: Evaluating the Latent Space of Deep Neural Networks using Local Neighborhood Analysis](https://mlsanity.com/paper/2312.04024/) (2023)
- [LayerFlow: Layer-wise Exploration of LLM Embeddings using Uncertainty-aware Interlinked Projections](https://mlsanity.com/paper/2504.10504/) (2025)
- ["Understanding Robustness Lottery": A Geometric Visual Comparative Analysis of Neural Network Pruning Approaches](https://mlsanity.com/paper/2206.07918/) (2022)
- [TopoAlign: Topology-Aware Visual Representation Alignment](https://mlsanity.com/paper/2605.25541/) (2026)
- [LatentVerse: A Framework for Understanding Shared and Modality-Specific Information in Multimodal Latent Representations](https://mlsanity.com/paper/2609.12364/) (2026)

## Abstract (arXiv)

Modern machine learning techniques commonly rely on complex, high-dimensional embedding representations to capture underlying structure in the data and improve performance. In order to characterize model flaws and choose a desirable representation, model builders often need to compare across multiple embedding spaces, a challenging analytical task supported by few existing tools. We first interviewed nine embedding experts in a variety of fields to characterize the diverse challenges they face and techniques they use when analyzing embedding spaces. Informed by these perspectives, we developed a novel system called Emblaze that integrates embedding space comparison within a computational notebook environment. Emblaze uses an animated, interactive scatter plot with a novel Star Trail augmentation to enable visual comparison. It also employs novel neighborhood analysis and clustering procedures to dynamically suggest groups of points with interesting changes between spaces. Through a series of case studies with ML experts, we demonstrate how interactive comparison with Emblaze can help gain new insights into embedding space structure.