Comparison-Based Inverse Classification for Interpretability in Machine Learning

Laugel, Thibault; Lesot, Marie‐Jeanne; Marsala, Christophe; Renard, Xavier; Detyniecki, Marcin

doi:10.1007/978-3-319-91473-2_9

Cited by 102 publications

(78 citation statements)

References 20 publications

(10 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The latter usually exploit the internal structure of the underlying ML model, such as the trained weights of a neural network, while the former are based on general principles which work for arbitrary ML models -often by only assuming access to the prediction function of an already fitted model. Several model-agnostic counterfactual methods have been proposed [8,11,16,18,25,29,37]. Apart from Grath et al [11], these approaches are limited to classification.…”

Section: Related Workmentioning

confidence: 99%

Multi-Objective Counterfactual Explanations

Dandl

Molnar

Binder

et al. 2020

Lecture Notes in Computer Science

160

125

View full text Add to dashboard Cite

Counterfactual explanations are one of the most popular methods to make predictions of black box machine learning models interpretable by providing explanations in the form of 'what-if scenarios'. Most current approaches optimize a collapsed, weighted sum of multiple objectives, which are naturally difficult to balance a-priori. We propose the Multi-Objective Counterfactuals (MOC) method, which translates the counterfactual search into a multi-objective optimization problem. Our approach not only returns a diverse set of counterfactuals with different trade-offs between the proposed objectives, but also maintains diversity in feature space. This enables a more detailed post-hoc analysis to facilitate better understanding and also more options for actionable user responses to change the predicted outcome. Our approach is also model-agnostic and works for numerical and categorical input features. We show the usefulness of MOC in concrete cases and compare our approach with state-of-the-art methods for counterfactual explanations.

show abstract

Section: Related Workmentioning

confidence: 99%

Multi-Objective Counterfactual Explanations

Dandl

Molnar

Binder

et al. 2020

Lecture Notes in Computer Science

160

125

View full text Add to dashboard Cite

show abstract

“…Subject to our experimental conditions, approximately 10 min were required for path planning per instance. A more practical path planning can be expected by combining our framework with techniques for finding intervention points, such as counterfactual explanations [41][42][43][44][45] .…”

Section: Discussionmentioning

confidence: 99%

Health improvement framework for planning actionable treatment process using surrogate Bayesian model

Nakamura

Kojima

Uchino

et al. 2020

Preprint

View full text Add to dashboard Cite

Clinical decision making regarding treatments based on personal characteristics leads to effective health improvements. Machine learning (ML) has been the primary concern of diagnosis support according to comprehensive patient information. However, the remaining prominent issue is the development of objective treatment processes in clinical situations. This study proposes a novel framework to plan treatment processes in a data-driven manner. A key point of the framework is the evaluation of the "actionability" for personal health improvements by using a surrogate Bayesian model in addition to a high-performance nonlinear ML model. We first evaluated the framework from the viewpoint of its methodology using a synthetic dataset. Subsequently, the framework was applied to an actual health checkup dataset comprising data from 3,132 participants, to improve systolic blood pressure values at the individual level. We confirmed that the computed treatment processes are actionable and consistent with clinical knowledge for lowering blood pressure. These results demonstrate that our framework could contribute toward decision making in the medical field, providing clinicians with deeper insights.

show abstract

“…Therefore, some authors find counterfactuals by applying ''smart'' iterative procedures in the input space [94] or search the counterfactual in a (growing) neighborhood of the starting point x; the neighborhood is enlarged until a counterfactual that allows to obtain the desired output is obtained [95]. Of note, some authors provide classifier interpretations that, though opposite to counterfactual explanations, allow anyway to interpret the classifier and provide counterfactuals.…”

Section: ) Explaining Prediction and Providing Suggestions With Counmentioning

confidence: 99%

“…In our work, after predicting the fitness score for a novel measurement x, the DT computes counterfactuals in a way similar to that used in [95].…”

Section: B Treating Novel Measurements To Provide Suggestions Based mentioning

confidence: 99%

Human Digital Twin for Fitness Management

et al. 2020

View full text Add to dashboard Cite

Our research work describes a team of human Digital Twins (DTs), each tracking fitness-related measurements describing an athlete's behavior in consecutive days (e.g. food income, activity, sleep). After collecting enough measurements, the DT firstly predicts the physical twin performance during training and, in case of non-optimal result, it suggests modifications in the athlete's behavior. The athlete's team is integrated into SmartFit, a software framework for supporting trainers and coaches in monitoring and manage athletes' fitness activity and results. Through IoT sensors embedded in wearable devices and applications for manual logging (e.g. mood, food income), SmartFit continuously captures measurements, initially treated as the dynamic data describing the current physical twins' status. Dynamic data allows adapting each DT's status and triggering the DT's predictions and suggestions. The analyzed measurements are stored as the historical data, further processed by the DT to update (increase) its knowledge and ability to provide reliable predictions. Results show that, thanks to the team of DTs, SmartFit computes trustable predictions of the physical twins' conditions and produces understandable suggestions which can be used by trainers to trigger optimization actions in the athletes' behavior. Though applied in the sport context, SmartFit can be easily adapted to other monitoring tasks. INDEX TERMS Counterfactual explanations, digital twins, Internet of Things, machine learning, smart health, sociotechnical design, wearables.

show abstract

Comparison-Based Inverse Classification for Interpretability in Machine Learning

Cited by 102 publications

References 20 publications

Multi-Objective Counterfactual Explanations

Multi-Objective Counterfactual Explanations

Health improvement framework for planning actionable treatment process using surrogate Bayesian model

Human Digital Twin for Fitness Management

Contact Info

Product

Resources

About