News and Views

Untangling the hairball using statistical inference

network visualization

methodological imperialism

TL;DR — Network visualization is often done in the wrong way: first a network layout is produced using a heuristic, and then follow-up analyses are performed and evaluated…

Tiago P. Peixoto

Hidden models and latent compression in community detection

community detection

This is an overdue post on a paper published last year with Alec Kirkley, named “Implicit Models, Latent Compression, Intrinsic Biases, and Cheap Lunches in Community…

Tiago P. Peixoto

Is Bayesian inference subjective?

community detection

In a previous blog post (covering [1]) I discussed how inferential approaches to community detection are based on the formulation of generative models, via the definition of…

Tiago P. Peixoto

Significant community structure via statistical tests?

community detection

statistical significance

In a previous blog post I explained how modularity maximization tends to overfit and find spurious community structure even in random graphs.

Tiago P. Peixoto

Do we need to believe in generative models?

community detection

In two previous blog posts (first and second) I advocated for the use of statistical inference for community detection in networks, whenever our objective is of an…

Tiago P. Peixoto

No free lunch in community detection?

community detection

For a wide class of optimization and learning problems there exist so-called “no-free-lunch” (NFL) theorems, which broadly state that when averaged over all possible problem…

Tiago P. Peixoto

Modularity maximization considered harmful

community detection

The most widespread method for community detection is modularity maximization [2], which happens also to be one of the most problematic. This method is based on the…

Tiago P. Peixoto

Inferring, explaining, and compressing

community detection

Inferential approaches to community detection (see [2] for a detailed introduction) are designed to provide explanations for network data in a principled manner. They are…

Tiago P. Peixoto

Descriptive vs. inferential community detection

community detection

Community detection is the task of dividing a network — typically one which is large — into many smaller groups of nodes that have a similar contribution to the overall…

Tiago P. Peixoto

Is network reconstruction impossible?

I have been getting some questions about a 2018 paper [1] by Jinyuan Chang, Eric D. Kolaczyk, and Qiwei Yao that deals with reconstruction of noisy networks, i.e. networks…

Tiago P. Peixoto