# Picking the two most distant classes

I have a big multi-label dataset which consist of thousands of classes. I would like to find the best way to choose the two most distant classes, i.e. classes that not only never co-exist but also are as little relevant to each other as possible. Ultimately, my goal is to covert this problem into a binary classification problem and use these results as a starting point. So, my question is, how to tackle this problem? Should I perform some sort of clustering with classical machine learning or I should see this as a big graph and use a network analysis package such as networkx?