A survey of visual analytics for Explainable Artificial Intelligence methods

Alicioğlu, Gülsüm; Sun, Bo

doi:10.1016/j.cag.2021.09.002

Cited by 107 publications

(36 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is often difficult to decide whether a paper is closer to SciVis than CV or CG. Ultimately, we check if the paper meets one of the two conditions for possible inclusion: (1) does the publication appear in a VIS venue? (2) has the publication significantly influenced SciVis work?…”

Section: Scope Of Surveymentioning

confidence: 99%

“…Generally speaking, there are two AI+VIS directions: AI4VIS (i.e., designing AI solutions for solving VIS problems) and VIS4AI (i.e., applying VIS techniques for explainable AI). We refer interested readers to recent surveys on AI+VIS [1], [22], [34], [69], [104], [150], [165], [172] to gain a comprehensive overview of this research area. These prior surveys focus on visual analytics (VA) and information visualization (InfoVis).…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we present DL4SciVis, a state-of-the-art survey on DL works for SciVis. Our aims are three-fold: (1) introducing researchers to the recent advances in DL4SciVis;…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

DL4SciVis: A State-of-the-Art Survey on Deep Learning for Scientific Visualization

Wang¹,

Han²

2022

Preprint

View full text Add to dashboard Cite

Since 2016, we have witnessed the tremendous growth of artificial intelligence+visualization (AI+VIS) research. However, existing survey papers on AI+VIS focus on visual analytics and information visualization, not scientific visualization (SciVis). In this paper, we survey related deep learning (DL) works in SciVis, specifically in the direction of DL4SciVis: designing DL solutions for solving SciVis problems. To stay focused, we primarily consider works that handle scalar and vector field data but exclude mesh data. We classify and discuss these works along six dimensions: domain setting, research task, learning type, network architecture, loss function, and evaluation metric. The paper concludes with a discussion of the remaining gaps to fill along the discussed dimensions and the grand challenges we need to tackle as a community. This state-of-the-art survey guides SciVis researchers in gaining an overview of this emerging topic and points out future directions to grow this research.

show abstract

Section: Scope Of Surveymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DL4SciVis: A State-of-the-Art Survey on Deep Learning for Scientific Visualization

Wang¹,

Han²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…A more elaborate taxonomy was proposed by Das et al [46], who considered dividing XAI techniques based on three criteria: scope (considering global or local explanations), methodology (if the technique focuses on the input data or model parameters), and usage (if is model-agnostic or model-specific). Regarding the scope, local explanations provide insights regarding a particular forecast, while global explanations attempt to describe the overall model behavior [47].…”

Section: Explainable Artificial Intelligencementioning

confidence: 99%

“…Scatterplots are frequently used to visualize data distribution, using some dimensionality reduction technique to map the high-dimensional dataset into two dimensions [57,58]. Color-coded instances are frequently used in classification tasks, and interactive interfaces provided, to enable the user focus on specific instances and conduct further research [47]. To represent feature contributions, horizontal bar plots [52,59,60], breakdown plots [61,62], heatmaps [63,64], Partial Dependence Plots [65], or Accumulated Local Effects Plots [66] are used.…”

Section: Explainable Artificial Intelligencementioning

confidence: 99%

Cyber-Physical LPG Debutanizer Distillation Columns: Machine-Learning-Based Soft Sensors for Product Quality Monitoring

Rožanec

Trajkova

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

Refineries execute a series of interlinked processes, where the product of one unit serves as the input to another process. Potential failures within these processes affect the quality of the end products, operational efficiency, and revenue of the entire refinery. In this context, implementation of a real-time cognitive module, referring to predictive machine learning models, enables the provision of equipment state monitoring services and the generation of decision-making for equipment operations. In this paper, we propose two machine learning models: (1) to forecast the amount of pentane (C5) content in the final product mixture; (2) to identify if C5 content exceeds the specification thresholds for the final product quality. We validate our approach using a use case from a real-world refinery. In addition, we develop a visualization to assess which features are considered most important during feature selection, and later by the machine learning models. Finally, we provide insights on the sensor values in the dataset, which help to identify the operational conditions for using such machine learning models.

show abstract

Explainable artificial intelligence: A taxonomy and guidelines for its application to drug discovery

Ponzoni

Prosper²,

Campillo

2023

WIREs Comput Mol Sci

View full text Add to dashboard Cite

Artificial intelligence (AI) is having a growing impact in many areas related to drug discovery. However, it is still critical for their adoption by the medicinal chemistry community to achieve models that, in addition to achieving high performance in their predictions, can be trusty explained to the end users in terms of their knowledge and background. Therefore, the investigation and development of explainable artificial intelligence (XAI) methods have become a key topic to address this challenge. For this reason, a comprehensive literature review about explanation methodologies for AI based models, focused in the field of drug discovery, is provided. In particular, an intuitive overview about each family of XAI approaches, such as those based on feature attribution, graph topologies, or counterfactual reasoning, oriented to a wide audience without a strong background in the AI discipline is introduced. As the main contribution, we propose a new taxonomy of the current XAI methods, which take into account specific issues related with the typical representations and computational problems study in the design of molecules. Additionally, we also present the main visualization strategies designed for supporting XAI approaches in the chemical domain. We conclude with key ideas about each method category, thoroughly providing insightful analysis about the guidelines and potential benefits of their adoption in medical chemistry.This article is categorized under: Data Science > Artificial Intelligence/Machine Learning

show abstract

A survey of visual analytics for Explainable Artificial Intelligence methods

Cited by 107 publications

References 46 publications

DL4SciVis: A State-of-the-Art Survey on Deep Learning for Scientific Visualization

DL4SciVis: A State-of-the-Art Survey on Deep Learning for Scientific Visualization

Cyber-Physical LPG Debutanizer Distillation Columns: Machine-Learning-Based Soft Sensors for Product Quality Monitoring

Explainable artificial intelligence: A taxonomy and guidelines for its application to drug discovery

Contact Info

Product

Resources

About