@inproceedings{27381,
  abstract     = {{Graph neural networks (GNNs) have been successfully applied in many structured data domains, with applications ranging from molecular property prediction to the analysis of social networks. Motivated by the broad applicability of GNNs, we propose the family of so-called RankGNNs, a combination of neural Learning to Rank (LtR) methods and GNNs. RankGNNs are trained with a set of pair-wise preferences between graphs, suggesting that one of them is preferred over the other. One practical application of this problem is drug screening, where an expert wants to find the most promising molecules in a large collection of drug candidates. We empirically demonstrate that our proposed pair-wise RankGNN approach either significantly outperforms or at least matches the ranking performance of the naive point-wise baseline approach, in which the LtR problem is solved via GNN-based graph regression.}},
  author       = {{Damke, Clemens and Hüllermeier, Eyke}},
  booktitle    = {{Proceedings of The 24th International Conference on Discovery Science (DS 2021)}},
  editor       = {{Soares, Carlos and Torgo, Luis}},
  isbn         = {{9783030889418}},
  issn         = {{0302-9743}},
  keywords     = {{Graph-structured data, Graph neural networks, Preference learning, Learning to rank}},
  location     = {{Halifax, Canada}},
  pages        = {{166--180}},
  publisher    = {{Springer}},
  title        = {{{Ranking Structured Objects with Graph Neural Networks}}},
  doi          = {{10.1007/978-3-030-88942-5}},
  volume       = {{12986}},
  year         = {{2021}},
}

@article{61025,
  abstract     = {{The concept of social dominance has been used in a plethora of studies to assess animal behaviour and relationships between individuals for nearly a century. Nevertheless, a standard approach does not yet exist to assess dominance in species that have a nonlinear or weakly linear hierarchical structure. We amassed 316 published data sets and show that 73.7% of the data sets and 90.3% of 103 species that we reviewed do not have a strongly linear structure. Herein, we present a novel method, ADAGIO, for assessing the structure of dominance networks. ADAGIO computes dominance hierarchies, in the form of directed acyclic graphs, to represent the dominance relations of a given group of animals. Thus far, most methods for computing dominance ranks assume implicitly that the dominance relation is a total order of the individuals in a group. ADAGIO does not assume or require this to be always true, and is hence more appropriate for analysing dominance hierarchies that are not strongly linear. We evaluated our approach against other frequently used methods, I&SI, David's score and Elo-rating, on 12 000 simulated data sets and on 279 interaction matrices from published, empirical data. The results from the simulated data show that ADAGIO achieves a significantly smaller error, and hence performs better when assigning ranks than other methods. Additionally, ADAGIO generated accurate dominance hierarchies for empirical data sets with a high index of linearity. Hence, our findings suggest that ADAGIO is currently the most reliable method to assess social dominance in gregarious animals living in groups of any size. Furthermore, since ADAGIO was designed to be generic, its applicability has the potential to extend beyond dominance data. The source code of our algorithm and all simulations used for this paper are publicly available at http://ngonga.github.io/adagio/.}},
  author       = {{Douglas, Pamela Heidi and Ngonga Ngomo, Axel-Cyrille and Hohmann, Gottfried}},
  issn         = {{0003-3472}},
  journal      = {{Animal Behaviour}},
  keywords     = {{aggression, behaviour, comparability, directed acyclic graph, hierarchy, linearity, nonlinearity, social rank, totality}},
  pages        = {{21--32}},
  publisher    = {{Elsevier BV}},
  title        = {{{A novel approach for dominance assessment in gregarious species: ADAGIO}}},
  doi          = {{10.1016/j.anbehav.2016.10.014}},
  volume       = {{123}},
  year         = {{2016}},
}

@article{3033,
  author       = {{Blömer, Johannes and Karp, Richard and Welzl, Emo}},
  journal      = {{Random Structures \& Algorithms}},
  keywords     = {{random matrices, rank, finite fields}},
  number       = {{4}},
  pages        = {{407--419}},
  title        = {{{The rank of sparse random matrices over finite fields}}},
  doi          = {{10.1002/(SICI)1098-2418(199707)10:4<407::AID-RSA1>3.0.CO;2-Y}},
  year         = {{1997}},
}