Interpretable feature subset selection: A Shapley value based approach

Tripathi, Sandhya; Hemachandra, N.; Trivedi, Prashant

doi:10.1109/bigdata50022.2020.9378102

Cited by 15 publications

(16 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Shapley values show how much a given feature changes the prediction compared to the prediction at the baseline value of that feature. The Shapley value [38]-based approach is being increasingly used by the machine learning community to deal with the interpretable feature subset selection problem [57].…”

Section: Age Prediction Analysismentioning

confidence: 99%

Prediction of Chronological Age in Healthy Elderly Subjects with Machine Learning from MRI Brain Segmentation and Cortical Parcellation

2022

View full text Add to dashboard Cite

Normal aging is associated with changes in volumetric indices of brain atrophy. A quantitative understanding of age-related brain changes can shed light on successful aging. To investigate the effect of age on global and regional brain volumes and cortical thickness, 3514 magnetic resonance imaging scans were analyzed using automated brain segmentation and parcellation methods in elderly healthy individuals (69–88 years of age). The machine learning algorithm extreme gradient boosting (XGBoost) achieved a mean absolute error of 2 years in predicting the age of new subjects. Feature importance analysis showed that the brain-to-intracranial-volume ratio is the most important feature in predicting age, followed by the hippocampi volumes. The cortical thickness in temporal and parietal lobes showed a superior predictive value than frontal and occipital lobes. Insights from this approach that integrate model prediction and interpretation may help to shorten the current explanatory gap between chronological age and biological brain age.

show abstract

Section: Age Prediction Analysismentioning

confidence: 99%

Prediction of Chronological Age in Healthy Elderly Subjects with Machine Learning from MRI Brain Segmentation and Cortical Parcellation

2022

View full text Add to dashboard Cite

show abstract

“…Thus, the Shapley value ϕ i is larger for data points that help more in minimizing the loss. Both the training or empirical loss [51] and validation loss [28] have been used to define v in machine learning research.…”

Section: The Shapley Valuementioning

confidence: 99%

“…Several works have explored the use of Shapley values in feature selection and importance. Here, the Shapley values of features quantify how much individual features contribute to the model's performance on a set of data points [25,18,8,40,51,50,24,53]. Several different approximation approaches have been proposed for the feature Shapley value.…”

Section: Related Workmentioning

confidence: 99%

“…Thus, it has been applied to understanding different elements in machine learning and is a popular tool in interpretable machine learning [38]. It is used to determine the importance of individual features [7,51], neurons [22], models in ensembles [43], data points [21,27] and many others (see [44]). However, the use of Shapley values is challenging from the perspectives of computation and privacy.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Differentially Private Shapley Values for Data Evaluation

Watson¹,

Andreeva²,

Yang³

et al. 2022

Preprint

View full text Add to dashboard Cite

The Shapley value has been proposed as a solution to many applications in machine learning, including for equitable valuation of data. Shapley values are computationally expensive and involve the entire dataset. The query for a point's Shapley value can also compromise the statistical privacy of other data points. We observe that in machine learning problems such as empirical risk minimization, and in many learning algorithms (such as those with uniform stability), a diminishing returns property holds, where marginal benefit per data point decreases rapidly with data sample size. Based on this property, we propose a new stratified approximation method called the Layered Shapley Algorithm. We prove that this method operates on small (O(polylog(n))) random samples of data and small sized (O(log n)) coalitions to achieve the results with guaranteed probabilistic accuracy, and can be modified to incorporate differential privacy. Experimental results show that the algorithm correctly identifies high-value data points that improve validation accuracy, and that the differentially private evaluations preserve approximate ranking of data.Preprint. Under review.

show abstract

“…Also, Amoukou et al (2021) investigated grouping approaches for Shapley values in the case of encoded categorical features and subset selection of important features for tree-based methods. The calculation of Shapley values on groups of features based on performance values has only been applied with regards to feature subset selection methods and not for interpretation purposes (Cohen et al, 2005;Tripathi et al, 2020).…”

Section: Related Workmentioning

confidence: 99%

Grouped Feature Importance and Combined Features Effect Plot

Au¹,

Herbinger²,

Stachl³

et al. 2021

Preprint

View full text Add to dashboard Cite

Interpretable machine learning has become a very active area of research due to the rising popularity of machine learning algorithms and their inherently challenging interpretability. Most work in this area has been focused on the interpretation of single features in a model. However, for researchers and practitioners, it is often equally important to quantify the importance or visualize the effect of feature groups. To address this research gap, we provide a comprehensive overview of how existing model-agnostic techniques can be defined for feature groups to assess the grouped feature importance, focusing on permutation-based, refitting, and Shapley-based methods. We also introduce an importance-based sequential procedure that identifies a stable and well-performing combination of features in the grouped feature space. Furthermore, we introduce the combined features effect plot, which is a technique to visualize the effect of a group of features based on a sparse, interpretable linear combination of features. We used simulation studies and a real data example from computational psychology to analyze, compare, and discuss these methods.

show abstract

Interpretable feature subset selection: A Shapley value based approach

Cited by 15 publications

References 24 publications

Prediction of Chronological Age in Healthy Elderly Subjects with Machine Learning from MRI Brain Segmentation and Cortical Parcellation

Prediction of Chronological Age in Healthy Elderly Subjects with Machine Learning from MRI Brain Segmentation and Cortical Parcellation

Differentially Private Shapley Values for Data Evaluation

Grouped Feature Importance and Combined Features Effect Plot

Contact Info

Product

Resources

About