Interpretability and Explainability: A Machine Learning Zoo Mini-tour

Marcinkevičs, Ričards; Vogt, Julia E.

doi:10.48550/arxiv.2012.01805

Cited by 41 publications

(51 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Interpretability mostly describes the methods that explain the underlying dynamics of opaque algorithms, such as deep neural networks. On the other hand, explainability usually refers to a set of post hoc added explanations for an existing model, understandable by lay users (Marcinkevičs & Vogt, 2020).…”

Section: Transparency and Explainabilitymentioning

confidence: 99%

Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspective

Kiritchenko,

Nejadgholi,

Fraser

2020

Preprint

View full text Add to dashboard Cite

The pervasiveness of abusive content on the internet can lead to severe psychological and physical harm. Significant effort in Natural Language Processing (NLP) research has been devoted to addressing this problem through abusive content detection and related sub-areas, such as the detection of hate speech, toxicity, cyberbullying, etc. Although current technologies achieve high classification performance in research studies, it has been observed that the real-life application of this technology can cause unintended harms, such as the silencing of under-represented groups. We review a large body of NLP research on automatic abuse detection with a new focus on ethical challenges, organized around eight established ethical principles: privacy, accountability, safety and security, transparency and explainability, fairness and non-discrimination, human control of technology, professional responsibility, and promotion of human values. In many cases, these principles relate not only to situational ethical codes, which may be context-dependent, but are in fact connected to universal human rights, such as the right to privacy, freedom from discrimination, and freedom of expression. We highlight the need to examine the broad social impacts of this technology, and to bring ethical and human rights considerations to every stage of the application life-cycle, from task formulation and dataset design, to model training and evaluation, to application deployment. Guided by these principles, we identify several opportunities for rights-respecting, socio-technical solutions to detect and confront online abuse, including 'nudging', 'quarantining', value sensitive design, counter-narratives, style transfer, and AI-driven public education applications.

show abstract

Section: Transparency and Explainabilitymentioning

confidence: 99%

Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspective

Kiritchenko,

Nejadgholi,

Fraser

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Explanation of these models and their predictions motivated developing a lot of methods and models which try to explain predictions of the deep classification and regression algorithms. There are several detailed survey papers providing a deep dive into variety of interpretation methods and models [7,23,31,35,36,54,57,60], which show an increasing importance of the interpretation methods and a growing interest to them.…”

Section: Introductionmentioning

confidence: 99%

Ensembles of Random SHAPs

Utkin,

Konstantinov

2021

Preprint

View full text Add to dashboard Cite

Ensemble-based modifications of the well-known SHapley Additive exPlanations (SHAP) method for the local explanation of a black-box model are proposed. The modifications aim to simplify SHAP which is computationally expensive when there is a large number of features. The main idea behind the proposed modifications is to approximate SHAP by an ensemble of SHAPs with a smaller number of features. According to the first modification, called ER-SHAP, several features are randomly selected many times from the feature set, and Shapley values for the features are computed by means of "small" SHAPs. The explanation results are averaged to get the final Shapley values. According to the second modification, called ERW-SHAP, several points are generated around the explained instance for diversity purposes, and results of their explanation are combined with weights depending on distances between points and the explained instance. The third modification, called ER-SHAP-RF, uses the random forest for preliminary explanation of instances and determining a feature probability distribution which is applied to selection of features in the ensemble-based procedure of ER-SHAP. Many numerical experiments illustrating the proposed modifications demonstrate their efficiency and properties for local explanation.

show abstract

“…Interpretation or explanation of decisions produced by learning models, including clustering, is a significant direction in machine learning (ML) and artificial intelligence (AI), and has given rise to the subfield of Explainable AI. Explainable AI has attracted a lot of attention from the researchers in recent years (see the surveys by Carvalho et al [5] and Marcinkevičs and Vogt [34]). All these works can be divided into two main categories: pre-modelling [43,42,23,15,30] and post-modelling [38,40,4,41,31] explainability.…”

Section: Introductionmentioning

confidence: 99%

How to Find a Good Explanation for Clustering?

Bandyapadhyay¹,

Fomin²,

Golovach³

et al. 2021

Preprint

View full text Add to dashboard Cite

k-means and k-median clustering are powerful unsupervised machine learning techniques. However, due to complicated dependences on all the features, it is challenging to interpret the resulting cluster assignments. Moshkovitz, Dasgupta, Rashtchian, and Frost [ICML 2020] proposed an elegant model of explainable k-means and k-median clustering. In this model, a decision tree with k leaves provides a straightforward characterization of the data set into clusters.We study two natural algorithmic questions about explainable clustering.(1) For a given clustering, how to find the "best explanation" by using a decision tree with k leaves? (2) For a given set of points, how to find a decision tree with k leaves minimizing the k-means/median objective of the resulting explainable clustering? To address the first question, we introduce a new model of explainable clustering. Our model, inspired by the notion of outliers in robust statistics, is the following. We are seeking a small number of points (outliers) whose removal makes the existing clustering well-explainable. For addressing the second question, we initiate the study of the model of Moshkovitz et al. from the perspective of multivariate complexity. Our rigorous algorithmic analysis sheds some light on the influence of parameters like the input size, dimension of the data, the number of outliers, the number of clusters, and the approximation ratio, on the computational complexity of explainable clustering.

show abstract

Interpretability and Explainability: A Machine Learning Zoo Mini-tour

Cited by 41 publications

References 77 publications

Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspective

Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspective

Ensembles of Random SHAPs

How to Find a Good Explanation for Clustering?

Contact Info

Product

Resources

About