ExplainExplore: Visual Exploration of Machine Learning Explanations

Collaris, Dennis; Wijk, Jarke J. van

doi:10.1109/pacificvis48177.2020.7090

Cited by 30 publications

(22 citation statements)

References 52 publications

(77 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach is popular in Machine Learning research [3,4], but adoption in the visualization community has been limited so far. Notable exceptions include Prospector [19], which uses 1D partial dependence as means to explore the prediction space, ExplainExplore [20] uses 2D partial dependence and incorporates feature contribution methods, and the Whatif tool [21] enables testing hypotheses by means of data perturbations. These systems enable the understanding of single predictions (local perspective) whereas STRATEGYATLAS aims to build an understanding of the model as a whole (multiple instances at once, or global perspective).…”

Section: Visualization For Model Analysismentioning

confidence: 99%

StrategyAtlas: Strategy Analysis for Machine Learning Interpretability

Collaris

Wijk

2023

IEEE Trans. Visual. Comput. Graphics

Self Cite

View full text Add to dashboard Cite

Businesses in high-risk environments have been reluctant to adopt modern machine learning approaches due to their complex and uninterpretable nature. Most current solutions provide local, instance-level explanations, but this is insufficient for understanding the model as a whole. In this work, we show that strategy clusters (i.e., groups of data instances that are treated distinctly by the model) can be used to understand the global behavior of a complex ML model. To support effective exploration and understanding of these clusters, we introduce STRATEGYATLAS, a system designed to analyze and explain model strategies. Furthermore, it supports multiple ways to utilize these strategies for simplifying and improving the reference model. In collaboration with a large insurance company, we present a use case in automatic insurance acceptance, and show how professional data scientists were enabled to understand a complex model and improve the production model based on these insights.

show abstract

Section: Visualization For Model Analysismentioning

confidence: 99%

StrategyAtlas: Strategy Analysis for Machine Learning Interpretability

Collaris

Wijk

2023

IEEE Trans. Visual. Comput. Graphics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Most of them focus on the visual presentation of such results. This includes saliency maps for Deep Neural Networks [ 57 ], task specific visualisations [ 58 ] and more general frameworks [ 59 ], which are still narrowed to only one phase of the DM process and hardly use any domain knowledge to enhance explanations nor interpretability of the models. For some examples, in [ 60 ], the authors demonstrate how the combination of deep tensor and knowledge graph embedding methods can be used for generating explanations for a model in intrusion detection and genomic medicine.…”

Section: Overview Of Semantic Data Mining Approachesmentioning

confidence: 99%

Semantic Data Mining in Ubiquitous Sensing: A Survey

Nalepa

Bobek

Kutt

et al. 2021

Sensors

View full text Add to dashboard Cite

Mining ubiquitous sensing data is important but also challenging, due to many factors, such as heterogeneous large-scale data that is often at various levels of abstraction. This also relates particularly to the important aspects of the explainability and interpretability of the applied models and their results, and thus ultimately to the outcome of the data mining process. With this, in general, the inclusion of domain knowledge leading towards semantic data mining approaches is an emerging and important research direction. This article aims to survey relevant works in these areas, focusing on semantic data mining approaches and methods, but also on selected applications of ubiquitous sensing in some of the most prominent current application areas. Here, we consider in particular: (1) environmental sensing; (2) ubiquitous sensing in industrial applications of artificial intelligence; and (3) social sensing relating to human interactions and the respective individual and collective behaviors. We discuss these in detail and conclude with a summary of this emerging field of research. In addition, we provide an outlook on future directions for semantic data mining in ubiquitous sensing contexts.

show abstract

“…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

ExplainExplore: Visual Exploration of Machine Learning Explanations

Cited by 30 publications

References 52 publications

StrategyAtlas: Strategy Analysis for Machine Learning Interpretability

StrategyAtlas: Strategy Analysis for Machine Learning Interpretability

Semantic Data Mining in Ubiquitous Sensing: A Survey

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

Contact Info

Product

Resources

About