@article{SteiningerKobsDavidsonetal.2021,
  author    = {Steininger, Michael and Kobs, Konstantin and Davidson, Padraig and Krause, Anna and Hotho, Andreas},
  title     = {Density-based weighting for imbalanced regression},
  series = {Machine Learning},
  volume    = {110},
  journal   = {Machine Learning},
  number    = {8},
  issn      = {1573-0565},
  doi       = {10.1007/s10994-021-06023-5},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-269177},
  pages     = {2187-2211},
  year      = {2021},
  abstract  = {In many real world settings, imbalanced data impedes model performance of learning algorithms, like neural networks, mostly for rare cases. This is especially problematic for tasks focusing on these rare occurrences. For example, when estimating precipitation, extreme rainfall events are scarce but important considering their potential consequences. While there are numerous well studied solutions for classification settings, most of them cannot be applied to regression easily. Of the few solutions for regression tasks, barely any have explored cost-sensitive learning which is known to have advantages compared to sampling-based methods in classification tasks. In this work, we propose a sample weighting approach for imbalanced regression datasets called DenseWeight and a cost-sensitive learning approach for neural network regression with imbalanced data called DenseLoss based on our weighting scheme. DenseWeight weights data points according to their target value rarities through kernel density estimation (KDE). DenseLoss adjusts each data point's influence on the loss according to DenseWeight, giving rare data points more influence on model training compared to common data points. We show on multiple differently distributed datasets that DenseLoss significantly improves model performance for rare data points through its density-based weighting scheme. Additionally, we compare DenseLoss to the state-of-the-art method SMOGN, finding that our method mostly yields better performance. Our approach provides more control over model training as it enables us to actively decide on the trade-off between focusing on common or rare cases through a single hyperparameter, allowing the training of better models for rare data points.},
  language  = {en}
}
@article{KoopmannStubbemannKapaetal.2021,
  author    = {Koopmann, Tobias and Stubbemann, Maximilian and Kapa, Matthias and Paris, Michael and Buenstorf, Guido and Hanika, Tom and Hotho, Andreas and J{\"a}schke, Robert and Stumme, Gerd},
  title     = {Proximity dimensions and the emergence of collaboration: a HypTrails study on German AI research},
  series = {Scientometrics},
  volume    = {126},
  journal   = {Scientometrics},
  number    = {12},
  issn      = {1588-2861},
  doi       = {10.1007/s11192-021-03922-1},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-269831},
  pages     = {9847-9868},
  year      = {2021},
  abstract  = {Creation and exchange of knowledge depends on collaboration. Recent work has suggested that the emergence of collaboration frequently relies on geographic proximity. However, being co-located tends to be associated with other dimensions of proximity, such as social ties or a shared organizational environment. To account for such factors, multiple dimensions of proximity have been proposed, including cognitive, institutional, organizational, social and geographical proximity. Since they strongly interrelate, disentangling these dimensions and their respective impact on collaboration is challenging. To address this issue, we propose various methods for measuring different dimensions of proximity. We then present an approach to compare and rank them with respect to the extent to which they indicate co-publications and co-inventions. We adapt the HypTrails approach, which was originally developed to explain human navigation, to co-author and co-inventor graphs. We evaluate this approach on a subset of the German research community, specifically academic authors and inventors active in research on artificial intelligence (AI). We find that social proximity and cognitive proximity are more important for the emergence of collaboration than geographic proximity.},
  language  = {en}
}