Counterfactual Explanations for Machine Learning: A Review
- URL: http://arxiv.org/abs/2010.10596v1
- Date: Tue, 20 Oct 2020 20:08:42 GMT
- Title: Counterfactual Explanations for Machine Learning: A Review
- Authors: Sahil Verma and John Dickerson and Keegan Hines
- Abstract summary: We review and categorize research on counterfactual explanations in machine learning.
Modern approaches to counterfactual explainability in machine learning draw connections to the established legal doctrine in many countries.
- Score: 5.908471365011942
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Machine learning plays a role in many deployed decision systems, often in
ways that are difficult or impossible to understand by human stakeholders.
Explaining, in a human-understandable way, the relationship between the input
and output of machine learning models is essential to the development of
trustworthy machine-learning-based systems. A burgeoning body of research seeks
to define the goals and methods of explainability in machine learning. In this
paper, we seek to review and categorize research on counterfactual
explanations, a specific class of explanation that provides a link between what
could have happened had input to a model been changed in a particular way.
Modern approaches to counterfactual explainability in machine learning draw
connections to the established legal doctrine in many countries, making them
appealing to fielded systems in high-impact areas such as finance and
healthcare. Thus, we design a rubric with desirable properties of
counterfactual explanation algorithms and comprehensively evaluate all
currently-proposed algorithms against that rubric. Our rubric provides easy
comparison and comprehension of the advantages and disadvantages of different
approaches and serves as an introduction to major research themes in this
field. We also identify gaps and discuss promising research directions in the
space of counterfactual explainability.
Related papers
- Beyond Model Interpretability: Socio-Structural Explanations in Machine Learning [5.159407277301709]
We argue that interpreting machine learning outputs in certain normatively salient domains could require appealing to a third type of explanation.
The relevance of this explanation type is motivated by the fact that machine learning models are not isolated entities but are embedded within and shaped by social structures.
arXiv Detail & Related papers (2024-09-05T15:47:04Z) - Explainability for Large Language Models: A Survey [59.67574757137078]
Large language models (LLMs) have demonstrated impressive capabilities in natural language processing.
This paper introduces a taxonomy of explainability techniques and provides a structured overview of methods for explaining Transformer-based language models.
arXiv Detail & Related papers (2023-09-02T22:14:26Z) - Machine Unlearning: A Survey [56.79152190680552]
A special need has arisen where, due to privacy, usability, and/or the right to be forgotten, information about some specific samples needs to be removed from a model, called machine unlearning.
This emerging technology has drawn significant interest from both academics and industry due to its innovation and practicality.
No study has analyzed this complex topic or compared the feasibility of existing unlearning solutions in different kinds of scenarios.
The survey concludes by highlighting some of the outstanding issues with unlearning techniques, along with some feasible directions for new research opportunities.
arXiv Detail & Related papers (2023-06-06T10:18:36Z) - Explainability in Machine Learning: a Pedagogical Perspective [9.393988089692947]
We provide a pedagogical perspective on how to structure the learning process to better impart knowledge to students and researchers in machine learning.
We discuss the advantages and disadvantages of various opaque and transparent machine learning models.
We will also discuss ways to structure potential assignments to best help students learn to use explainability as a tool alongside any given machine learning application.
arXiv Detail & Related papers (2022-02-21T16:15:57Z) - Rethinking Explainability as a Dialogue: A Practitioner's Perspective [57.87089539718344]
We ask doctors, healthcare professionals, and policymakers about their needs and desires for explanations.
Our study indicates that decision-makers would strongly prefer interactive explanations in the form of natural language dialogues.
Considering these needs, we outline a set of five principles researchers should follow when designing interactive explanations.
arXiv Detail & Related papers (2022-02-03T22:17:21Z) - Explainable Machine Learning with Prior Knowledge: An Overview [1.1045760002858451]
The complexity of machine learning models has elicited research to make them more explainable.
We propose to harness prior knowledge to improve upon the explanation capabilities of machine learning models.
arXiv Detail & Related papers (2021-05-21T07:33:22Z) - Individual Explanations in Machine Learning Models: A Survey for
Practitioners [69.02688684221265]
The use of sophisticated statistical models that influence decisions in domains of high societal relevance is on the rise.
Many governments, institutions, and companies are reluctant to their adoption as their output is often difficult to explain in human-interpretable ways.
Recently, the academic literature has proposed a substantial amount of methods for providing interpretable explanations to machine learning models.
arXiv Detail & Related papers (2021-04-09T01:46:34Z) - Knowledge as Invariance -- History and Perspectives of
Knowledge-augmented Machine Learning [69.99522650448213]
Research in machine learning is at a turning point.
Research interests are shifting away from increasing the performance of highly parameterized models to exceedingly specific tasks.
This white paper provides an introduction and discussion of this emerging field in machine learning research.
arXiv Detail & Related papers (2020-12-21T15:07:19Z) - Machine Learning Explainability for External Stakeholders [27.677158604772238]
There have been growing calls to open the black box and to make machine learning algorithms more explainable.
We conducted a day-long workshop with academics, industry experts, legal scholars, and policymakers to develop a shared language around explainability.
We provide a short summary of various case studies of explainable machine learning, lessons from those studies, and discuss open challenges.
arXiv Detail & Related papers (2020-07-10T14:27:06Z) - A general framework for scientifically inspired explanations in AI [76.48625630211943]
We instantiate the concept of structure of scientific explanation as the theoretical underpinning for a general framework in which explanations for AI systems can be implemented.
This framework aims to provide the tools to build a "mental-model" of any AI system so that the interaction with the user can provide information on demand and be closer to the nature of human-made explanations.
arXiv Detail & Related papers (2020-03-02T10:32:21Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.