Matches in SemOpenAlex for { <https://semopenalex.org/work/W3081430106> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W3081430106 endingPage "115" @default.
- W3081430106 startingPage "97" @default.
- W3081430106 abstract "Machine Learning is enjoying an increasing success in many applications: medical, marketing, defence, cyber security, transportation. It is becoming a key tool in critical systems. However, models are often very complex and highly non-linear. This is problematic, especially for critical systems, because end-users need to fully understand the decisions of an algorithm (e.g. why an alert has been triggered or why a person has a high probability of cancer recurrence). One solution is to offer an interpretation for each individual prediction based on attribute relevance. Shapley Values allow to distribute fairly contributions for each attribute in order to understand the difference between a predicted value for an observation and a base value (e.g. the average prediction of a reference population). They come from cooperative game theory. While these values have many advantages, including their theoretical guarantees, they are however really hard to calculate. Indeed, the complexity increases exponentially with the dimension (the number of variables). In this article, we propose two novel methods to approximate these Shapley Values. The first one is an optimization of an already existing Monte Carlo scheme. It reduces the number of prediction function calls. The second method is based on a projected gradient stochastic algorithm. We prove for the second approach some probability bounds and convergence rates for the approximation errors according to the learning rate type used. Finally, we carry out experiments on simulated datasets for a classification and a regression task. We empirically show that these approaches outperform the classical Monte Carlo estimator in terms of convergence rate and number of prediction function calls, which is the major bottleneck in Shapley Value estimation for our application." @default.
- W3081430106 created "2020-09-01" @default.
- W3081430106 creator A5013211255 @default.
- W3081430106 creator A5047263783 @default.
- W3081430106 date "2020-01-01" @default.
- W3081430106 modified "2023-09-25" @default.
- W3081430106 title "A Projected Stochastic Gradient Algorithm for Estimating Shapley Value Applied in Attribute Importance" @default.
- W3081430106 cites W1980412153 @default.
- W3081430106 cites W1992208280 @default.
- W3081430106 cites W2008918413 @default.
- W3081430106 cites W2129888542 @default.
- W3081430106 cites W2583836055 @default.
- W3081430106 cites W2787894218 @default.
- W3081430106 cites W2911964244 @default.
- W3081430106 cites W2981731882 @default.
- W3081430106 cites W3013917854 @default.
- W3081430106 cites W3082455399 @default.
- W3081430106 doi "https://doi.org/10.1007/978-3-030-57321-8_6" @default.
- W3081430106 hasPublicationYear "2020" @default.
- W3081430106 type Work @default.
- W3081430106 sameAs 3081430106 @default.
- W3081430106 citedByCount "3" @default.
- W3081430106 countsByYear W30814301062021 @default.
- W3081430106 countsByYear W30814301062022 @default.
- W3081430106 countsByYear W30814301062023 @default.
- W3081430106 crossrefType "book-chapter" @default.
- W3081430106 hasAuthorship W3081430106A5013211255 @default.
- W3081430106 hasAuthorship W3081430106A5047263783 @default.
- W3081430106 hasBestOaLocation W30814301062 @default.
- W3081430106 hasConcept C11413529 @default.
- W3081430106 hasConcept C119857082 @default.
- W3081430106 hasConcept C126255220 @default.
- W3081430106 hasConcept C144237770 @default.
- W3081430106 hasConcept C177142836 @default.
- W3081430106 hasConcept C199022921 @default.
- W3081430106 hasConcept C2776291640 @default.
- W3081430106 hasConcept C28826006 @default.
- W3081430106 hasConcept C33923547 @default.
- W3081430106 hasConcept C41008148 @default.
- W3081430106 hasConceptScore W3081430106C11413529 @default.
- W3081430106 hasConceptScore W3081430106C119857082 @default.
- W3081430106 hasConceptScore W3081430106C126255220 @default.
- W3081430106 hasConceptScore W3081430106C144237770 @default.
- W3081430106 hasConceptScore W3081430106C177142836 @default.
- W3081430106 hasConceptScore W3081430106C199022921 @default.
- W3081430106 hasConceptScore W3081430106C2776291640 @default.
- W3081430106 hasConceptScore W3081430106C28826006 @default.
- W3081430106 hasConceptScore W3081430106C33923547 @default.
- W3081430106 hasConceptScore W3081430106C41008148 @default.
- W3081430106 hasLocation W30814301061 @default.
- W3081430106 hasLocation W30814301062 @default.
- W3081430106 hasLocation W30814301063 @default.
- W3081430106 hasLocation W30814301064 @default.
- W3081430106 hasOpenAccess W3081430106 @default.
- W3081430106 hasPrimaryLocation W30814301061 @default.
- W3081430106 hasRelatedWork W2002181330 @default.
- W3081430106 hasRelatedWork W2014821034 @default.
- W3081430106 hasRelatedWork W2031588308 @default.
- W3081430106 hasRelatedWork W2069939853 @default.
- W3081430106 hasRelatedWork W2143789917 @default.
- W3081430106 hasRelatedWork W2386767533 @default.
- W3081430106 hasRelatedWork W3125718624 @default.
- W3081430106 hasRelatedWork W4214514662 @default.
- W3081430106 hasRelatedWork W4379654729 @default.
- W3081430106 hasRelatedWork W79233177 @default.
- W3081430106 isParatext "false" @default.
- W3081430106 isRetracted "false" @default.
- W3081430106 magId "3081430106" @default.
- W3081430106 workType "book-chapter" @default.