# Building and Interpreting Deep Similarity Models

arXiv: https://arxiv.org/abs/2003.05431 · HTML: https://mlsanity.com/paper/2003.05431/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2020.

## Built on by (most cited first, 30 of 34)

- [MambaLRP: Explaining Selective State Space Sequence Models](https://mlsanity.com/paper/2406.07592/) (2024)
- [Toward Explainable AI for Regression Models](https://mlsanity.com/paper/2112.11407/) (2021)
- [Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces](https://mlsanity.com/paper/2212.14855/) (2022)
- [The Clever Hans Effect in Unsupervised Learning](https://mlsanity.com/paper/2408.08041/) (2024)
- [ReSi: A Comprehensive Benchmark for Representational Similarity Measures](https://mlsanity.com/paper/2408.00531/) (2024)
- [PredDiff: Explanations and Interactions from Conditional Expectations](https://mlsanity.com/paper/2102.13519/) (2021)
- [xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology](https://mlsanity.com/paper/2406.04280/) (2024)
- [Label-Free Explainability for Unsupervised Models](https://mlsanity.com/paper/2203.01928/) (2022)
- [RelP: Faithful and Efficient Circuit Discovery in Language Models via Relevance Patching](https://mlsanity.com/paper/2508.21258/) (2025)
- [Interpretable Text Embeddings and Text Similarity Explanation: A Survey](https://mlsanity.com/paper/2502.14862/) (2025)
- [Explaining Predictive Uncertainty by Exposing Second-Order Effects](https://mlsanity.com/paper/2401.17441/) (2024)
- [Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework](https://mlsanity.com/paper/2506.15538/) (2025)
- [Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks](https://mlsanity.com/paper/2304.05727/) (2023)
- [Explaining Text Similarity in Transformer Models](https://mlsanity.com/paper/2405.06604/) (2024)
- [Visualizing and Understanding Contrastive Learning](https://mlsanity.com/paper/2206.09753/) (2022)
- [Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features](https://mlsanity.com/paper/2408.17198/) (2024)
- [Sparse, Efficient and Explainable Data Attribution with DualXDA](https://mlsanity.com/paper/2402.12118/) (2024)
- [Improving a neural network model by explanation-guided training for glioma classification based on MRI data](https://mlsanity.com/paper/2107.02008/) (2021)
- [Position: We Need An Algorithmic Understanding of Generative AI](https://mlsanity.com/paper/2507.07544/) (2025)
- [A Rigorous Study Of The Deep Taylor Decomposition](https://mlsanity.com/paper/2211.08425/) (2022)
- [Insightful analysis of historical sources at scales beyond human capabilities using unsupervised Machine Learning and XAI](https://mlsanity.com/paper/2310.09091/) (2023)
- [Explaining Caption-Image Interactions in CLIP Models with Second-Order Attributions](https://mlsanity.com/paper/2408.14153/) (2024)
- [Order-Level Attention Similarity Across Language Models: A Latent Commonality](https://mlsanity.com/paper/2511.05064/) (2025)
- [Beyond Attention Heatmaps: How to Get Better Explanations for Multiple Instance Learning Models in Histopathology](https://mlsanity.com/paper/2603.08328/) (2026)
- [Normalized Relevance Measure as a Unifying Framework to Explain Neural Network Latent Structures](https://mlsanity.com/paper/2606.00557/) (2026)
- [Cat, Rat, Meow: On the Alignment of Language Model and Human Term-Similarity Judgments](https://mlsanity.com/paper/2504.07965/) (2025)
- [Relevant Walk Search for Explaining Graph Neural Networks](https://mlsanity.com/paper/2605.23673/) (2026)
- [It's FLAN time! Summing feature-wise latent representations for interpretability](https://mlsanity.com/paper/2106.10086/) (2021)
- [Restricted Receptive Fields for Face Verification](https://mlsanity.com/paper/2510.10753/) (2025)
- [When LRP Diverges from Leave-One-Out in Transformers](https://mlsanity.com/paper/2510.18810/) (2025)

## Abstract (arXiv)

Many learning algorithms such as kernel machines, nearest neighbors, clustering, or anomaly detection, are based on the concept of 'distance' or 'similarity'. Before similarities are used for training an actual machine learning model, we would like to verify that they are bound to meaningful patterns in the data. In this paper, we propose to make similarities interpretable by augmenting them with an explanation in terms of input features. We develop BiLRP, a scalable and theoretically founded method to systematically decompose similarity scores on pairs of input features. Our method can be expressed as a composition of LRP explanations, which were shown in previous works to scale to highly nonlinear functions. Through an extensive set of experiments, we demonstrate that BiLRP robustly explains complex similarity models, e.g. built on VGG-16 deep neural network features. Additionally, we apply our method to an open problem in digital humanities: detailed assessment of similarity between historical documents such as astronomical tables. Here again, BiLRP provides insight and brings verifiability into a highly engineered and problem-specific similarity model.