%Aigaion2 BibTeX export from Knowledge Engineering Publications
%Friday 17 December 2021 11:56:43 PM

@INPROCEEDINGS{kauschke18mil,
     author = {Kauschke, Sebastian and M{\"{u}}hlh{\"{a}}user, Max and F{\"{u}}rnkranz, Johannes},
   keywords = {Bag Classification, Denoising Autoencoder, Multi-Instance Learning, Reproduction-Error Representation},
      month = oct,
      title = {Leveraging Reproduction-Error Representations for Multi-Instance Classification},
  booktitle = {Proceedings of the 21st International Conference on Discovery Science - DS'18},
     series = {Lecture Notes on Artificial Intelligence},
     volume = {11198},
       year = {2018},
      pages = {83-95},
  publisher = {Springer Nature Switzerland AG},
   location = {Limassol, Cyprus},
        doi = {https://doi.org/10.1007/978-3-030-01771-2_6},
   abstract = {Multi-instance learning deals with the problem of classifying
bags of instances, when only the labels of the bags are known for
learning, and the instances themselves have no labels. In this work, we
propose a method that trains autoencoders for the instances in each
class, and recodes each instance into a representation that captures the
reproduction error for this instance. The idea behind this approach is
that an autoencoder trained on only instances of a single class is unable
to reproduce examples from another class properly, which is then
reflected in the encoding. The transformed instances are then piped into
a propositional classifier that decides the latent instance label. In a second
classification layer, the bag label is decided based on the output of
the propositional classifier on all the instances in the bag. We show that
this reproduction-error encoding creates an advantage compared to the
classification of non-encoded data, and that further research into this
direction could be beneficial for the cause of multi-instance learning.}
}