Explainable, Normative, and Justified Agency

Langley, Pat

doi:10.1609/aaai.v33i01.33019775

Cited by 16 publications

(13 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, even if the word "justification" is not used in the paper, [25] introduces an "explicability" principle for AI taken "both in the epistemological sense of 'intelligibility' and in the ethical sense of 'accountability'". The normative nature of justifications was also mentioned in the field of intelligent systems [48]: "an intelligent system exhibits justified agency if it follows society's norms and explains its activities in those terms." However, these norms are not characterized precisely in [48].…”

Section: Related Workmentioning

confidence: 99%

Beyond explainability: justifiability and contestability of algorithmic decision systems

Henin

Métayer

2021

AI & Soc

View full text Add to dashboard Cite

In this paper, we point out that explainability is useful but not sufficient to ensure the legitimacy of algorithmic decision systems. We argue that the key requirements for high stakes decision systems should be justifiability and contestability. We highlight the conceptual differences between explanations and justifications and suggest different ways to operationalize justifiability and contestability.

show abstract

Section: Related Workmentioning

confidence: 99%

Beyond explainability: justifiability and contestability of algorithmic decision systems

Henin

Métayer

2021

AI & Soc

View full text Add to dashboard Cite

show abstract

“…Figure presents the working procedure of the filters. Filter methods attempt to use evaluation criteria based on statistical theory and information theory such as distance function, statistical correlation coefficient, mutual information, etc., to assess the relevance of the features and rank them according to their importance. Then the features with high scores are used in the ML model.…”

Section: Preliminariesmentioning

confidence: 99%

Multi‐Layer Feature Selection Incorporating Weighted Score‐Based Expert Knowledge toward Modeling Materials with Targeted Properties

Liu

Avdeev

et al. 2020

Advcd Theory and Sims

View full text Add to dashboard Cite

Selecting proper descriptors or features is one of the central problems in exploring structure–activity relationships of materials using machine learning models. The current feature selection algorithms usually require tedious hyperparameter tuning and do not actively consider the prior knowledge of domain experts about the features. Here, this work proposes a data‐driven multi‐layer feature selection method incorporating domain expert knowledge named DML‐FSdek, which is automated, with users entering training data without manual tuning of the hyperparameters. The domain expert knowledge is quantified by means of weighted scoring and integrated into the selection process to eliminate the risk of crucial features being removed. The test studies on ten material properties datasets demonstrate the potential of the approach to automatically search for a reduced feature set with lower root mean square errors than those for the initial feature set. Essentially, the most relevant material features, the number of which is much smaller than that in the original feature set, are automatically selected to establish a closer and more accurate structure–activity relationship for the materials of interest. As a result, the method represents the targeted properties of materials with a smaller and more interpretable set of features while ensuring equal or better prediction accuracy.

show abstract

“…Regarding the extrinsic nature of explanation, [31] distinguishes between justifications and explanations based on the origin of the information they refer to: explanations describe how the system works while justifications use domain knowledge to show that decisions are correct. The normative nature of justifications has also been pointed out in the field of intelligent systems [18]: "an intelligent system exhibits justified agency if it follows society's norms and explains its activities in those terms". In [19], the authors qualify explanations as "unjustified" when there are not supported by training data, which is related to our notion of justification with reference-based norms (Sect.…”

Section: Related Workmentioning

confidence: 99%

A framework to contest and justify algorithmic decisions

Henin

Métayer

2021

AI Ethics

View full text Add to dashboard Cite

In this paper, we argue that the possibility of contesting the results of Algorithmic Decision Systems (ADS) is a key requirement for ADS used to make decisions with a high impact on individuals. We discuss the limitations of explanations and motivate the need for better facilities to contest or justify the results of an ADS. While the goal of an explanation is to make it possible for a human being to understand, the goal of a justification is to convince that the decision is good or appropriate. To claim that a result is good, it is necessary (1) to refer to an independent definition of what a good result is (the norm) and(2) to provide evidence that the norm applies to the case. Based on these definitions, we present a challenge and justification framework including three types of norms, a proof-of-concept implementation of this framework and its application to a credit decision system.

show abstract

Explainable, Normative, and Justified Agency

Cited by 16 publications

References 11 publications

Beyond explainability: justifiability and contestability of algorithmic decision systems

Beyond explainability: justifiability and contestability of algorithmic decision systems

Multi‐Layer Feature Selection Incorporating Weighted Score‐Based Expert Knowledge toward Modeling Materials with Targeted Properties

A framework to contest and justify algorithmic decisions

Contact Info

Product

Resources

About