mlsanityData to 14 Oct 2026

The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizations

arXiv 2212.11737 ↗First posted 22 Dec 2022cs.LG cs.HC stat.MLcited by 29

Not on the map. Why?

Abstract (arXiv)

Machine learning (ML) models are nowadays used in complex applications in various domains, such as medicine, bioinformatics, and other sciences. Due to their black box nature, however, it may sometimes be hard to understand and trust the results they provide. This has increased the demand for reliable visualization tools related to enhancing trust in ML models, which has become a prominent topic of research in the visualization community over the past decades. To provide an overview and present the frontiers of current research on the topic, we present a State-of-the-Art Report (STAR) on enhancing trust in ML models with the use of interactive visualization. We define and describe the background of the topic, introduce a categorization for visualization techniques that aim to accomplish this goal, and discuss insights and opportunities for future research directions. Among our contributions is a categorization of trust against different facets of interactive ML, expanded and improved from previous research. Our results are investigated from different analytical perspectives: (a) providing a statistical overview, (b) summarizing key findings, (c) performing topic analyses, and (d) exploring the data sets used in the individual papers, all with the support of an interactive web-based survey browser. We intend this survey to be beneficial for visualization researchers whose interests involve making ML models more trustworthy, as well as researchers and practitioners from other disciplines in their search for effective visualization techniques suitable for solving their tasks with confidence and conveying meaning to their data.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). Builds on 69 of its 463 references that are in the map. First posted on arXiv 22 Dec 2022.

Builds on

69 of 463 references.

References · 69

  1. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  4. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  5. 2016Inherent Trade-Offs in the Fair Determination of Risk Scorescited by 586
  6. 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
  7. 2015Understanding Neural Networks Through Deep Visualizationcited by 334
  8. 2018On the Robustness of Interpretability Methodscited by 314
  9. 2018Learning to Explain: An Information-Theoretic Perspective on Model Interpretationcited by 248
  10. 2018Techniques for Interpretable Machine Learningcited by 238
  11. 2016Model-Agnostic Interpretability of Machine Learningcited by 219
  12. 2019The What-If Tool: Interactive Probing of Machine Learning Modelscited by 207
38 more
  1. 2017Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Modelscited by 206
  2. 2020Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthycited by 183
  3. 2014SimLex-999: Evaluating Semantic Models with (Genuine) Similarity Estimationcited by 172
  4. 2018Visual Interpretability for Deep Learning: a Surveycited by 155
  5. 2018Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontierscited by 117
  6. 2019FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learningcited by 93
  7. 2019The relationship between trust in AI and trustworthy machine learning technologiescited by 78
  8. 2019Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizationscited by 72
  9. 2019Interpretable and Steerable Sequence Learning via Prototypescited by 72
  10. 2019explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learningcited by 70
  11. 2018Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Modelscited by 69
  12. 2018RuleMatrix: Visualizing and Understanding Classifiers with Rulescited by 62
  13. 2017Do Convolutional Neural Networks Learn Class Hierarchy?cited by 61
  14. 2018RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Recordscited by 61
  15. 2019FairSight: Visual Analytics for Fairness in Decision Makingcited by 59
  16. 2017ActiVis: Visual Exploration of Industry-Scale Deep Neural Network Modelscited by 56
  17. 2018What can AI do for me: Evaluating Machine Learning Interpretations in Cooperative Playcited by 53
  18. 2016Towards Better Analysis of Deep Convolutional Neural Networkscited by 51
  19. 2018Manifold: A Model-Agnostic Framework for Interpretation and Diagnosis of Machine Learning Modelscited by 50
  20. 2017The paradigm-shift of social spambots: Evidence, theories, and tools for the arms racecited by 49
  21. 2017Understanding Hidden Memories of Recurrent Neural Networkscited by 44
  22. 2018GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentationcited by 41
  23. 2018Visual Analytics for Explainable Deep Learningcited by 39
  24. 2017Towards Better Analysis of Machine Learning Models: A Visual Analytics Perspectivecited by 36
  25. 2018Defining Locality for Surrogates in Post-hoc Interpretablitycited by 33
  26. 2018Clustrophile 2: Guided Visual Clustering Analysiscited by 26
  27. 2019Supporting Analysis of Dimensionality Reduction Results with Contrastive Learningcited by 26
  28. 2018The State of the Art in Integrating Machine Learning into Visual Analyticscited by 24
  29. 2019Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analyticscited by 24
  30. 2019Visual Interaction with Deep Learning Models through Collaborative Semantic Inferencecited by 24
  31. 2019ATMSeer: Increasing Transparency and Controllability in Automated Machine Learningcited by 23
  32. 2017A Workflow for Visual Diagnostics of Binary Classifiers using Instance-Level Explanationscited by 20
  33. 2015Approximated and User Steerable tSNE for Progressive Visual Analyticscited by 19
  34. 2014Assessment of algorithms for mitosis detection in breast cancer histopathology imagescited by 16
  35. 2018A Visual Interaction Framework for Dimensionality Reduction Based Data Explorationcited by 15
  36. 2018A User-based Visual Analytics Workflow for Exploratory Model Analysiscited by 12
  37. 2019NNVA: Neural Network Assisted Visual Analysis of Yeast Cell Polarization Simulationcited by 12
  38. 2017SkyLens: Visual Analysis of Skyline on Multi-dimensional Datacited by 9

50 most cited of 69 All 69 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 11; 2024: 9; 2025: 7; 2026: 1.

29 papers.

Sort:

  1. 2023Visual Analytics For Machine Learning: A Data Perspective Surveycited by 25
  2. 2023When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence Systemcited by 13
  3. 2023Out-of-distribution detection algorithms for robust insect classificationcited by 7
  4. 2023AutoDOViz: Human-Centered Automation for Decision Optimizationcited by 3
  5. 2023Visual Analytics of Multivariate Networks with Representation Learning and Composite Variable Constructioncited by 3
  6. 2024Visualization for Trust in Machine Learning Revisited: The State of the Field in 2023cited by 3
  7. 2025Visual Analytics for Explainable and Trustworthy Artificial Intelligencecited by 3
  8. 2023DeforestVis: Behavior Analysis of Machine Learning Models with Surrogate Decision Stumpscited by 2
  9. 2023Visualization for Recommendation Explainability: A Survey and New Perspectivescited by 2
  10. 2023Visual Validation versus Visual Estimation: A Study on the Average Value in Scatterplotscited by 2
  11. 2023Towards the Visualization of Aggregated Class Activation Maps to Analyse the Global Contribution of Class Featurescited by 2
  12. 2024DimVis: Interpreting Visual Clusters in Dimensionality Reduction With Explainable Boosting Machinecited by 2
17 more
  1. 2024Adversarial Attacks on Machine Learning-Aided Visualizationscited by 2
  2. 2023SKG: A Versatile Information Retrieval and Analysis Framework for Academic Papers with Semantic Knowledge Graphscited by 1
  3. 2024U-Trustworthy Models.Reliability, Competence, and Confidence in Decision-Makingcited by 1
  4. 2024Recent advances in interpretable machine learning using structure-based protein representationscited by 1
  5. 2025Comparing Native and Non-native English Speakers' Behaviors in Collaborative Writing through Visual Analyticscited by 1
  6. 2025Cluster-Based Random Forest Visualization and Interpretationcited by 1
  7. 2022Challenges in anomaly and change point detectioncited by 0
  8. 2023LINGO : Visually Debiasing Natural Language Instructions to Support Task Diversitycited by 0
  9. 2024Towards Robust Training Datasets for Machine Learning with Ontologies: A Case Study for Emergency Road Vehicle Detectioncited by 0
  10. 2024Leveraging Hybrid Intelligence Towards Sustainable and Energy-Efficient Machine Learningcited by 0
  11. 2024Beware of Validation by Eye: Visual Validation of Linear Trends in Scatterplotscited by 0
  12. 2024Who should I trust? A Visual Analytics Approach for Comparing Net Load Forecasting Modelscited by 0
  13. 2025The Human-Data-Model Interaction Canvas for Visual Analyticscited by 0
  14. 2025TS-Insight: Visualizing Thompson Sampling for Verification and XAIcited by 0
  15. 2025VAR: Visual Analysis for Rashomon Set of Machine Learning Models' Performancecited by 0
  16. 2025CityAQVis: Integrated ML-Visualization Sandbox Tool for Pollutant Estimation in Urban Regions Using Multi-Source Data (Software Article)cited by 0
  17. 2026Understanding How Humans Inject Knowledge into Machine Learning Workflows through Visual Analyticscited by 0