Publications (new)
2024
Sánchez-Olivares, E.; Boekhout, H. D.; Saxena, A.; Takes, F. W.
A Framework for Empirically Evaluating Pretrained Link Prediction Models Proceedings Article
In: Cherifi, H.; Rocha, L. M.; Cherifi, C.; Donduran, M. (Ed.): Complex Networks & Their Applications XII. Proceedings of the 12th International Conference on Complex Networks (Complex Networks 2023), pp. 150–161, Springer Nature Switzerland, Cham, 2024, ISBN: 978-3-031-53468-3.
Abstract | Links | BibTeX | Tags: Link Prediction, Pretrained Models, Transfer Learning
@inproceedings{sanchez_olivares_framework_2024,
title = {A Framework for Empirically Evaluating Pretrained Link Prediction Models},
author = {E. Sánchez-Olivares and H. D. Boekhout and A. Saxena and F. W. Takes},
editor = {H. Cherifi and L. M. Rocha and C. Cherifi and M. Donduran},
doi = {10.1007/978-3-031-53468-3_13},
isbn = {978-3-031-53468-3},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
booktitle = {Complex Networks & Their Applications XII. Proceedings of the 12th International Conference on Complex Networks (Complex Networks 2023)},
pages = {150–161},
publisher = {Springer Nature Switzerland},
address = {Cham},
abstract = {This paper proposes a novel framework for empirically assessing the effect of network characteristics on the performance of pretrained link prediction models. In link prediction, the task is to predict missing or future links in a given network dataset. We focus on the pretrained setting, in which such a predictive model is trained on one dataset, and employed on another dataset. The framework allows one to overcome a number of nontrivial challenges in adequately testing the performance of such a pretrained model in a proper cross-validated setting. Experiments are performed on a corpus of 49 structurally diverse real-world complex network datasets from various domains with up to hundreds of thousands of nodes and edges. Overall results indicate that the extent to which a network is clustered is strongly related to whether this network is a suitable candidate to create a pretrained model on. Moreover, we systematically assessed the relationship between topological similarity and performance difference of pretrained models and a model trained on the same data. We find that similar network pairs in terms of clustering coefficient, and to a lesser extent degree assortativity and gini coefficient, yield minimal performance difference. The findings presented in this work pave the way for automated model selection based on topological similarity of the networks, as well as larger-scale deployment of pretrained link prediction models for transfer learning.},
keywords = {Link Prediction, Pretrained Models, Transfer Learning},
pubstate = {published},
tppubtype = {inproceedings}
}
2021
Bruin, G. J.; Veenman, C. J.; Herik, H. J.; Takes, F. W.
Experimental Evaluation of Train and Test Split Strategies in Link Prediction Proceedings Article
In: Benito, Rosa M.; Cherifi, C.; Cherifi, H.; Moro, E.; Rocha, L. M.; Sales-Pardo, M. (Ed.): Complex Networks & Their Applications IX, pp. 79–91, Springer International Publishing, Cham, 2021, ISBN: 978-3-030-65351-4.
Abstract | Links | BibTeX | Tags: Link Prediction, Machine learning, Performance estimation
@inproceedings{de_bruin_experimental_2021,
title = {Experimental Evaluation of Train and Test Split Strategies in Link Prediction},
author = {G. J. Bruin and C. J. Veenman and H. J. Herik and F. W. Takes},
editor = {Rosa M. Benito and C. Cherifi and H. Cherifi and E. Moro and L. M. Rocha and M. Sales-Pardo},
doi = {10.1007/978-3-030-65351-4_7},
isbn = {978-3-030-65351-4},
year = {2021},
date = {2021-01-01},
booktitle = {Complex Networks & Their Applications IX},
pages = {79–91},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {In link prediction, the goal is to predict which links will appear in the future of an evolving network. To estimate the performance of these models in a supervised machine learning model, disjoint and independent train and test sets are needed. However, objects in a real-world network are inherently related to each other. Therefore, it is far from trivial to separate candidate links into these disjoint sets.},
keywords = {Link Prediction, Machine learning, Performance estimation},
pubstate = {published},
tppubtype = {inproceedings}
}
2020
Bruin, G. J.; Veenman, C. J.; Herik, H. J.; Takes, F. W.
Understanding Dynamics of Truck Co-Driving Networks Proceedings Article
In: Cherifi, H.; Gaito, S.; Mendes, J. F.; Moro, E.; Rocha, L. M. (Ed.): Complex Networks and Their Applications VIII, pp. 140–151, Springer International Publishing, Cham, 2020, ISBN: 978-3-030-36683-4.
Abstract | Links | BibTeX | Tags: Co-driving behaviour, Link Prediction, Mobility, Spatio-temporal networks, Transport networks
@inproceedings{de_bruin_understanding_2020,
title = {Understanding Dynamics of Truck Co-Driving Networks},
author = {G. J. Bruin and C. J. Veenman and H. J. Herik and F. W. Takes},
editor = {H. Cherifi and S. Gaito and J. F. Mendes and E. Moro and L. M. Rocha},
doi = {10.1007/978-3-030-36683-4_12},
isbn = {978-3-030-36683-4},
year = {2020},
date = {2020-01-01},
booktitle = {Complex Networks and Their Applications VIII},
pages = {140–151},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {The goal of this paper is to learn the dynamics of truck co-driving behaviour. Understanding this behaviour is important because co-driving has a potential positive impact on the environment. In the so-called co-driving network, trucks are nodes while links indicate that two trucks frequently drive together. To understand the network’s dynamics, we use a link prediction approach employing a machine learning classifier. The features of the classifier can be categorized into spatio-temporal features, neighbourhood features, path features, and node features. The very different types of features allow us to understand the social processes underlying the co-driving behaviour. Our work is based on a spatio-temporal data not studied before. Data is collected from 18 million truck movements in the Netherlands. We find that co-driving behaviour is best described by using neighbourhood features, and to lesser extent by path and spatio-temporal features. Node features are deemed unimportant. Findings suggest that the dynamics of a truck co-driving network has clear social network effects.},
keywords = {Co-driving behaviour, Link Prediction, Mobility, Spatio-temporal networks, Transport networks},
pubstate = {published},
tppubtype = {inproceedings}
}