# Explainable embeddings with Distance Explainer

arXiv: https://arxiv.org/abs/2505.15516 · HTML: https://mlsanity.com/paper/2505.15516/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 47 references that are in the map.
- First posted on arXiv 21 May 2025.

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [An Introduction to Variational Autoencoders](https://mlsanity.com/paper/1906.02691/) (2019)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [On the (In)fidelity and Sensitivity for Explanations](https://mlsanity.com/paper/1901.09392/) (2019)
- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Understanding the Role of Individual Units in a Deep Neural Network](https://mlsanity.com/paper/2009.05041/) (2020)
- [Evaluating and Aggregating Feature-based Model Explanations](https://mlsanity.com/paper/2005.00631/) (2020)
- [Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond](https://mlsanity.com/paper/2202.06861/) (2022)
- [From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation](https://mlsanity.com/paper/2206.03208/) (2022)
- [Unbox the Black-box for the Medical Explainable AI via Multi-modal and Multi-centre Data Fusion: A Mini-Review, Two Showcases and Beyond](https://mlsanity.com/paper/2102.01998/) (2021)
- [Visually grounded models of spoken language: A survey of datasets, architectures and evaluation techniques](https://mlsanity.com/paper/2104.13225/) (2021)
- [Using Sequences of Life-events to Predict Human Lives](https://mlsanity.com/paper/2306.03009/) (2023)
- [A Survey on Understanding, Visualizations, and Explanation of Deep Neural Networks](https://mlsanity.com/paper/2102.01792/) (2021)
- [Towards Visual Saliency Explanations of Face Verification](https://mlsanity.com/paper/2305.08546/) (2023)
- [Sanity Checks Revisited: An Exploration to Repair the Model Parameter Randomisation Test](https://mlsanity.com/paper/2401.06465/) (2024)
- [Explanation of Face Recognition via Saliency Maps](https://mlsanity.com/paper/2304.06118/) (2023)

## Built on by (most cited first, 1 of 1)

- [Partition-Guided Distance Saliency: Bridging Decision and Objective Spaces in Many-Objective Optimization](https://mlsanity.com/paper/2606.30836/) (2026)

## Abstract (arXiv)

While eXplainable AI (XAI) has advanced significantly, few methods address interpretability in embedded vector spaces where dimensions represent complex abstractions. We introduce Distance Explainer, a novel method for generating local, post-hoc explanations of embedded spaces in machine learning models. Our approach adapts saliency-based techniques from RISE to explain the distance between two embedded data points by assigning attribution values through selective masking and distance-ranked mask filtering. We evaluate Distance Explainer on cross-modal embeddings (image-image and image-caption pairs) using established XAI metrics including Faithfulness, Sensitivity/Robustness, and Randomization. Experiments with ImageNet and CLIP models demonstrate that our method effectively identifies features contributing to similarity or dissimilarity between embedded data points while maintaining high robustness and consistency. We also explore how parameter tuning, particularly mask quantity and selection strategy, affects explanation quality. This work addresses a critical gap in XAI research and enhances transparency and trustworthiness in deep learning applications utilizing embedded spaces.