Explaining a series of models by propagating Shapley values
University of Washington · Seattle University · +1 more institution
Abstract
Local feature attribution methods are increasingly used to explain complex machine learning models. However, current methods are limited because they are extremely expensive to compute or are not capable of explaining a distributed series of models where each model is owned by a separate institution. The latter is particularly important because it often arises in finance where explanations are mandated. Here, we present Generalized DeepSHAP (G-DeepSHAP), a tractable method to propagate local feature attributions through complex series of models based on a connection to the Shapley value. We evaluate G-DeepSHAP across biological, health, and financial datasets to show that it provides equally salient…
Citation impact
- FWCI
- 25.66
- Percentile
- 100%
- References
- 53
Authors
3Topics & keywords
- Salient
- Shapley value
- Computer science
- Series (stratigraphy)
- Attribution
- Feature (linguistics)
- Machine learning
- Econometrics
Funding
- NSNational Science FoundationAwards: 1552309, 1256082, 1759487, DGE-1256082, DBI-1759487, 1762114, -1762114, DGE-1762114, DBI-1552309
- IDIllinois Department of Public HealthAwards: P30AG10161, R01AG15819, R01AG17917
- RURush University
- TGTranslational Genomics Research Institute
- CRCancer Research UK
- NINational Institutes of HealthAwards: R01 NIA AG 061132, R35 GM 128638, U01AG46152, R01AG17917, R01AG15819, U01AG46161, R01AG36836, P30AG10161, DGE-1256082
- NINational Institute on AgingAwards: U01AG46161, R01AG17917, R01AG36836, R01AG15819, U01AG46152, P30AG10161