% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Tesch:897359,
author = {Tesch, Tobias and Kollet, Stefan and Garcke, Jochen},
title = {{V}ariant {A}pproach for {I}dentifying {S}purious
{R}elations that {D}eep {L}earning {M}odels {L}earn},
journal = {Frontiers in water},
volume = {3},
issn = {2624-9375},
address = {Lausanne},
publisher = {Frontiers Media},
reportid = {FZJ-2021-03747},
pages = {745563},
year = {2021},
abstract = {A deep learning (DL) model learns a function relating a set
of input variables with a set of target variables. While the
representation of this function in form of the DL model
often lacks interpretability, several interpretation methods
exist that provide descriptions of the function (e.g.,
measures of feature importance). On the one hand, these
descriptions may build trust in the model or reveal its
limitations. On the other hand, they may lead to new
scientific understanding. In any case, a description is only
useful if one is able to identify if parts of it reflect
spurious instead of causal relations (e.g., random
associations in the training data instead of associations
due to a physical process). However, this can be challenging
even for experts because, in scientific tasks, causal
relations between input and target variables are often
unknown or extremely complex. Commonly, this challenge is
addressed by training separate instances of the considered
model on random samples of the training set and identifying
differences between the obtained descriptions. Here, we
demonstrate that this may not be sufficient and propose to
additionally consider more general modifications of the
prediction task. We refer to the proposed approach as
variant approach and demonstrate its usefulness and its
superiority over pure sampling approaches with two
illustrative prediction tasks from hydrometeorology. While
being conceptually simple, to our knowledge the approach has
not been formalized and systematically evaluated before.},
cin = {IBG-3},
ddc = {333.7},
cid = {I:(DE-Juel1)IBG-3-20101118},
pnm = {2173 - Agro-biogeosystems: controls, feedbacks and impact
(POF4-217)},
pid = {G:(DE-HGF)POF4-2173},
typ = {PUB:(DE-HGF)16},
UT = {WOS:000705052600001},
doi = {10.3389/frwa.2021.745563},
url = {https://juser.fz-juelich.de/record/897359},
}