New work on the arxiv: "Network reconstruction and community detection from dynamics",
I show how coupling Bayesian network reconstruction from functional behavior with community detection enhances both tasks simultaneously.
Just out on PRX: "Reconstructing Networks with Unknown and Heterogeneous Errors"
New method can reconstruct networks and provide error estimates for them, even when measurement uncertainties are unknown.
Code is available as part of graph-tool: https://graph-tool.skewed.de
The documentation for the reconstruction code is here: https://graph-tool.skewed.de/static/doc/demos/inference/inference.html#network-reconstruction
Each integer is represented in a high-dimensional space, and gets squished down to 2D so that numbers with similar prime factorisations are closer together than those with dissimilar factorisations.
"Science starts with a question. Data science starts with the data. What makes data science so hard is that it starts in the wrong place."
Great analogy of scientific protocol with law & order episodes!
Now I can't get the title song out of my head.
Finally on the arXiv: "Reconstructing networks with unknown and heterogeneous errors" https://arxiv.org/abs/1806.07956
Did you know you can reconstruct and make error estimates for networks, by making only a single noisy measurement?
Physics & Networks
social.skewed.de is one server in the network