English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Shapley values are great analytical tools in game theory to measure theimportance of a player in a game. Due to their axiomatic and desirableproperties such as efficiency, they have become popular for feature importanceanalysis in data science and machine learning. However, the time complexity tocompute Shapley values based on the original formula is exponential, and as thenumber of features increases, this becomes infeasible. Castro et al. [1]developed a sampling algorithm, to estimate Shapley values. In this work, wepropose a new sampling method based on a multilinear extension technique asapplied in game theory. The aim is to provide a more efficient (sampling)method for estimating Shapley values. Our method is applicable to any machinelearning model, in particular for either multi-class classifications orregression problems. We apply the method to estimate Shapley values formultilayer perceptrons (MLPs) and through experimentation on two datasets, wedemonstrate that our method provides more accurate estimations of the Shapleyvalues by reducing the variance of the sampling statistics.

A Multilinear Sampling Algorithm to Estimate Shapley Values