Towards Generating Consumer Labels for Machine Learning Models

Seifert, Christin; Scherzinger, Stefanie; Wiese, Lena

doi:10.1109/cogmi48466.2019.00033

Cited by 14 publications

(6 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…"Best is not directly a judgment of truth but instead a summary judgment of accessible explanatory virtues" [119]. In practice, such a multi-dimensional overview could be implemented as a radar chart or as a set of consumer labels as proposed by Seifert et al [221] that comprehensively and concisely conveys the strengths and weaknesses of the explanation or explanation method. Our collection of identified evaluation methods also shows that quantitative evaluation methods exist for each of the Co-12 properties.…”

Section: Implications and Research Opportunitiesmentioning

confidence: 99%

From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI

Nauta¹,

Trienes²,

Pathak³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The rising popularity of explainable artificial intelligence (XAI) to understand high-performing black boxes, also raised the question of how to evaluate explanations of machine learning (ML) models. While interpretability and explainability are often presented as a subjectively validated binary property, we consider it a multi-faceted concept. We identify 12 conceptual properties, such as Compactness and Correctness, that should be evaluated for comprehensively assessing the quality of an explanation. Our so-called Co-12 properties serve as categorization scheme for systematically reviewing the evaluation practice of more than 300 papers published in the last 7 years at major AI and ML conferences that introduce an XAI method. We find that 1 in 3 papers evaluate exclusively with anecdotal evidence, and 1 in 5 papers evaluate with users. We also contribute to the call for objective, quantifiable evaluation methods by presenting an extensive overview of quantitative XAI evaluation methods. This systematic collection of evaluation methods provides researchers and practitioners with concrete tools to thoroughly validate, benchmark and compare new and existing XAI methods. This also opens up opportunities to include quantitative metrics as optimization criteria during model training in order to optimize for accuracy and interpretability simultaneously.

show abstract

Section: Implications and Research Opportunitiesmentioning

confidence: 99%

From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI

Nauta¹,

Trienes²,

Pathak³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Under the banner of increased transparency, there are a number of initiatives and an ever-growing list of tools deployed towards the mitigation of bias in ADS. Broadly speaking, these tools aim to provide transparency at the system, model, and data levels [29].…”

Section: Related Workmentioning

confidence: 99%

The Dataset Nutrition Label (2nd Gen): Leveraging Context to Mitigate Harms in Artificial Intelligence

Chmielinski¹,

Newman²,

Taylor³

et al. 2022

Preprint

View full text Add to dashboard Cite

As the production of and reliance on datasets to produce automated decisionmaking systems (ADS) increases, so does the need for processes for evaluating and interrogating the underlying data. After launching the Dataset Nutrition Label in 2018, the Data Nutrition Project has made significant updates to the design and purpose of the Label, and is launching an updated Label in late 2020, which is previewed in this paper. The new Label includes context-specific Use Cases & Alerts presented through an updated design and user interface targeted towards the data scientist profile. This paper discusses the harm and bias from underlying training data that the Label is intended to mitigate, the current state of the work including new datasets being labeled, new and existing challenges, and further directions of the work, as well as Figures previewing the new label.

show abstract

“…If we want to give certain guarantees for the correctness of data engineering processes in advance without knowing the concrete datasets, we have to know the behaviour and characteristics of each of the algorithms. For machine learning approaches, this idea has been introduced in [18] and [19].…”

Section: Analysis Of Algorithms and Specification Of Contractsmentioning

confidence: 99%

Kurz erklärt: Measuring Data Changes in Data Engineering and their Impact on Explainability and Algorithm Fairness

2021

View full text Add to dashboard Cite

Data engineering is an integral part of any data science and ML process. It consists of several subtasks that are performed to improve data quality and to transform data into a target format suitable for analysis. The quality and correctness of the data engineering steps is therefore important to ensure the quality of the overall process.In machine learning processes requirements such as fairness and explainability are essential. The answers to these must also be provided by the data engineering subtasks. In this article, we will show how these can be achieved by logging, monitoring and controlling the data changes in order to evaluate their correctness. However, since data preprocessing algorithms are part of any machine learning pipeline, they must obviously also guarantee that they do not produce data biases.In this article we will briefly introduce three classes of methods for measuring data changes in data engineering and present which research questions still remain unanswered in this area.

show abstract

Towards Generating Consumer Labels for Machine Learning Models

Cited by 14 publications

References 33 publications

From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI

From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI

The Dataset Nutrition Label (2nd Gen): Leveraging Context to Mitigate Harms in Artificial Intelligence

Kurz erklärt: Measuring Data Changes in Data Engineering and their Impact on Explainability and Algorithm Fairness

Contact Info

Product

Resources

About