# Survey of explainable machine learning with visual and granular methods beyond quasi-explanations

arXiv: https://arxiv.org/abs/2009.10221 · HTML: https://mlsanity.com/paper/2009.10221/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Sep 2020.

## Built on by (most cited first, 20 of 20)

- [Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities](https://mlsanity.com/paper/2111.06420/) (2021)
- [Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysis](https://mlsanity.com/paper/2208.10609/) (2022)
- [The role of causality in explainable artificial intelligence](https://mlsanity.com/paper/2309.09901/) (2023)
- [Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View](https://mlsanity.com/paper/2112.02625/) (2021)
- [Discovering Interpretable Machine Learning Models in Parallel Coordinates](https://mlsanity.com/paper/2106.07474/) (2021)
- [New Money: A Systematic Review of Synthetic Data Generation for Finance](https://mlsanity.com/paper/2510.26076/) (2025)
- [Full interpretable machine learning in 2D with inline coordinates](https://mlsanity.com/paper/2106.07568/) (2021)
- [Non-linear Visual Knowledge Discovery with Elliptic Paired Coordinates](https://mlsanity.com/paper/2107.04974/) (2021)
- [Rule Induction in Knowledge Graphs Using Linear Programming](https://mlsanity.com/paper/2110.08245/) (2021)
- [Self-service Data Classification Using Interactive Visualization and Interpretable Machine Learning](https://mlsanity.com/paper/2107.04971/) (2021)
- [Visual Knowledge Discovery with Artificial Intelligence: Challenges and Future Directions](https://mlsanity.com/paper/2205.01296/) (2022)
- [Visual Knowledge Discovery with General Line Coordinates](https://mlsanity.com/paper/2305.18429/) (2023)
- [Highly Accurate Disease Diagnosis and Highly Reproducible Biomarker Identification with PathFormer](https://mlsanity.com/paper/2402.07268/) (2024)
- [Interpretable Machine Learning for Self-Service High-Risk Decision-Making](https://mlsanity.com/paper/2205.04032/) (2022)
- [A survey and taxonomy of methods interpreting random forest models](https://mlsanity.com/paper/2407.12759/) (2024)
- [Explainable Mixed Data Representation and Lossless Visualization Toolkit for Knowledge Discovery](https://mlsanity.com/paper/2206.06476/) (2022)
- [Parallel Coordinates for Discovery of Interpretable Machine Learning Models](https://mlsanity.com/paper/2305.18434/) (2023)
- [Explainable Machine Learning for Categorical and Mixed Data with Lossless Visualization](https://mlsanity.com/paper/2305.18437/) (2023)
- [Full High-Dimensional Intelligible Learning In 2-D Lossless Visualization Space](https://mlsanity.com/paper/2305.19132/) (2023)
- [Interpetable Target-Feature Aggregation for Multi-Task Learning based on Bias-Variance Analysis](https://mlsanity.com/paper/2406.07991/) (2024)

## Abstract (arXiv)

This paper surveys visual methods of explainability of Machine Learning (ML) with focus on moving from quasi-explanations that dominate in ML to domain-specific explanation supported by granular visuals. ML interpretation is fundamentally a human activity and visual methods are more readily interpretable. While efficient visual representations of high-dimensional data exist, the loss of interpretable information, occlusion, and clutter continue to be a challenge, which lead to quasi-explanations. We start with the motivation and the different definitions of explainability. The paper focuses on a clear distinction between quasi-explanations and domain specific explanations, and between explainable and an actually explained ML model that are critically important for the explainability domain. We discuss foundations of interpretability, overview visual interpretability and present several types of methods to visualize the ML models. Next, we present methods of visual discovery of ML models, with the focus on interpretable models, based on the recently introduced concept of General Line Coordinates (GLC). These methods take the critical step of creating visual explanations that are not merely quasi-explanations but are also domain specific visual explanations while these methods themselves are domain-agnostic. The paper includes results on theoretical limits to preserve n-D distances in lower dimensions, based on the Johnson-Lindenstrauss lemma, point-to-point and point-to-graph GLC approaches, and real-world case studies. The paper also covers traditional visual methods for understanding ML models, which include deep learning and time series models. We show that many of these methods are quasi-explanations and need further enhancement to become domain specific explanations. We conclude with outlining open problems and current research frontiers.