% 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},
}