Here you can find a consolidated (a.k.a. slowly updated) list of my publications. A frequently updated (and possibly noisy) list of works is available on my Google Scholar profile.
Please find below a short list of highlight publications for my recent activity.
Errica, Federico; Gravina, Alessio; Bacciu, Davide; Micheli, Alessio
Hidden Markov Models for Temporal Graph Representation Learning Conference
Proceedings of the 31th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning , 2023.
@conference{Errica2023,
title = {Hidden Markov Models for Temporal Graph Representation Learning},
author = {Federico Errica and Alessio Gravina and Davide Bacciu and Alessio Micheli},
editor = {Michel Verleysen},
year = {2023},
date = {2023-10-04},
urldate = {2023-10-04},
booktitle = {Proceedings of the 31th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning },
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Atzeni, Daniele; Bacciu, Davide; Errica, Federico; Micheli, Alessio
Modeling Edge Features with Deep Bayesian Graph Networks Conference
Proceedings of the International Joint Conference on Neural Networks (IJCNN 2021), IEEE IEEE, 2021.
@conference{Atzeni2021,
title = { Modeling Edge Features with Deep Bayesian Graph Networks},
author = {Daniele Atzeni and Davide Bacciu and Federico Errica and Alessio Micheli},
doi = {10.1109/IJCNN52387.2021.9533430},
year = {2021},
date = {2021-07-18},
urldate = {2021-07-18},
booktitle = {Proceedings of the International Joint Conference on Neural Networks (IJCNN 2021)},
publisher = {IEEE},
organization = {IEEE},
abstract = {We propose an extension of the Contextual Graph Markov Model, a deep and probabilistic machine learning model for graphs, to model the distribution of edge features. Our approach is architectural, as we introduce an additional Bayesian network mapping edge features into discrete states to be used by the original model. In doing so, we are also able to build richer graph representations even in the absence of edge features, which is confirmed by the performance improvements on standard graph classification benchmarks. Moreover, we successfully test our proposal in a graph regression scenario where edge features are of fundamental importance, and we show that the learned edge representation provides substantial performance improvements against the original model on three link prediction tasks. By keeping the computational complexity linear in the number of edges, the proposed model is amenable to large-scale graph processing.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
We propose an extension of the Contextual Graph Markov Model, a deep and probabilistic machine learning model for graphs, to model the distribution of edge features. Our approach is architectural, as we introduce an additional Bayesian network mapping edge features into discrete states to be used by the original model. In doing so, we are also able to build richer graph representations even in the absence of edge features, which is confirmed by the performance improvements on standard graph classification benchmarks. Moreover, we successfully test our proposal in a graph regression scenario where edge features are of fundamental importance, and we show that the learned edge representation provides substantial performance improvements against the original model on three link prediction tasks. By keeping the computational complexity linear in the number of edges, the proposed model is amenable to large-scale graph processing.
Bacciu, Davide; Lisboa, Paulo J. G.; Sperduti, Alessandro; Villmann, Thomas
Probabilistic Modeling in Machine Learning Book Chapter
In: Kacprzyk, Janusz; Pedrycz, Witold (Ed.): pp. 545–575, Springer Berlin Heidelberg, Berlin, Heidelberg, 2015, ISBN: 978-3-662-43505-2.
@inbook{Bacciu2015,
title = {Probabilistic Modeling in Machine Learning},
author = {Davide Bacciu and Paulo J.G. Lisboa and Alessandro Sperduti and Thomas Villmann},
editor = {Janusz Kacprzyk and Witold Pedrycz},
url = {http://dx.doi.org/10.1007/978-3-662-43505-2_31},
doi = {10.1007/978-3-662-43505-2_31},
isbn = {978-3-662-43505-2},
year = {2015},
date = {2015-01-01},
urldate = {2015-01-01},
pages = {545--575},
publisher = {Springer Berlin Heidelberg},
address = {Berlin, Heidelberg},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
Davide, Bacciu; Alessio, Micheli; Alessandro, Sperduti
Compositional Generative Mapping for Tree-Structured Data - Part II: Topographic Projection Model Journal Article
In: Neural Networks and Learning Systems, IEEE Transactions on, vol. 24, no. 2, pp. 231 -247, 2013, ISSN: 2162-237X.
@article{gmtsdII2012,
title = {Compositional Generative Mapping for Tree-Structured Data - Part II: Topographic Projection Model},
author = {Bacciu Davide and Micheli Alessio and Sperduti Alessandro},
url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6395856},
doi = {10.1109/TNNLS.2012.2228226},
issn = {2162-237X},
year = {2013},
date = {2013-02-01},
journal = {Neural Networks and Learning Systems, IEEE Transactions on},
volume = {24},
number = {2},
pages = {231 -247},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Davide, Bacciu; Alessio, Micheli; Alessandro, Sperduti
An input–output hidden Markov model for tree transductions Journal Article
In: Neurocomputing, vol. 112, pp. 34–46, 2013, ISSN: 0925-2312.
@article{bacciuNeuroComp2013,
title = {An input–output hidden Markov model for tree transductions},
author = {Bacciu Davide and Micheli Alessio and Sperduti Alessandro },
url = {http://www.sciencedirect.com/science/article/pii/S0925231213001914},
doi = {10.1016/j.neucom.2012.12.044},
issn = {0925-2312},
year = {2013},
date = {2013-01-01},
journal = {Neurocomputing},
volume = {112},
pages = {34--46},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Davide, Bacciu; Alessio, Micheli; Alessandro, Sperduti
Compositional Generative Mapping for Tree-Structured Data; Part I: Bottom-Up Probabilistic Modeling of Trees Journal Article
In: Neural Networks and Learning Systems, IEEE Transactions on, vol. 23, no. 12, pp. 1987 -2002, 2012, ISSN: 2162-237X.
@article{gmtsdI2012,
title = {Compositional Generative Mapping for Tree-Structured Data; Part I: Bottom-Up Probabilistic Modeling of Trees},
author = {Bacciu Davide and Micheli Alessio and Sperduti Alessandro},
url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6353263},
doi = {10.1109/TNNLS.2012.2222044},
issn = {2162-237X},
year = {2012},
date = {2012-12-01},
journal = {Neural Networks and Learning Systems, IEEE Transactions on},
volume = {23},
number = {12},
pages = {1987 -2002},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
