Anomaly, reciprocity, and community detection in networks is now published in Physical Review Research! We propose a probabilistic generative approach that incorporates community membership and reciprocity as key factors driving regular behaviour in a network, which can be used to identify potential anomalies that deviate from expected patterns. Both the paper and the code of CRAD are available online.

Our work on Community detection in large hypergraphs is published in Science Advances. We propose a principled framework to model the organization of higher-order data through the detection of overlapping communities. Read it here and check out the code of Hy-MMSBM.

Stay tuned because our work on Community Detection in Large Hypergraphs got accepted for publication in Science Advances.

The paper that describes hypergraphx (HGX), our new Python library for higher-order network analysis, is published in the Journal of Complex Networks! Read it here and check the library.​

I will be a panellist @NetSci2023 during the panel discussion The Write Way Forward: a Panel on Academic Writing, organized by NetPLACE. Join us on Monday, July 10th, at 17.30! 

HGX, our new Python library for higher-order network analysis, is out! It is freely available on GitHub​ and the preprint is out on arXiv.​

My abstract got accepted for a regular talk @NetSci2023! Stay Tuned :)

I'll present a method to perform inference in heterogeneous and attributed multilayer networks.

Finally out! Latent network models to account for noisy, multiply reported social network data is published in the Journal of the Royal Statistical Society Series A: Statistics in Society. The paper is available online and the implementation of VIMuRe is available both in R and Python.

New preprint out: Anomaly, reciprocity, and community detection in networks. You can read it on arXiv.

New preprint out: Generalized Inference of Mesoscale Structures in Higher-order Networks. We propose a principled framework to model the organization of higher-order data. Check it out on arXiv and take a look at the code too. 

Inference of hyperedges and overlapping communities in hypergraphs is now published in Nature Communications. We propose a framework based on statistical inference to characterize the structural organization of hypergraphs. Read it here and check the Python implementation of Hypergraph-MT. 

I presented Hypergaph-MT @TopoNets22, in Palma de Mallorca during the Conference on Complex Systems 2022.

I presented JointCRep during the European Social Networks Conference 2022, in London. It is a probabilistic generative model and an efficient algorithm to both perform community detection and capture reciprocity in networks. This approach jointly models pairs of edges with exact 2-edge joint distributions, and provides closed-form analytical expressions for both marginal and conditional distributions.