La Torre d’En Rovira.

We walk under the scorching sun for two hours, in and out of the pine groves where old hippies live in old trucks, not knowing where we’re going except for the fact that we’re moving North. We’re looking for a place to escape the crowded August of the island.

When considering relational problems, the temporal dimension is often crucial to understand whether the process behind the relational graph is evolving, and how; think how often people follow and unfollow each other on Instagram, how the type of content in one’s posts may change over time, and how all of these aspects are echoed throughout the network, interacting with one another in complex ways.

While most works that apply deep learning to temporal networks are focused on the evolution of the graph at the node or edge level, it is extremely interesting to study a graph-based process from a global perspective, at the graph level, to detect trends and changes in the process itself.

Ever since I started getting closer to machine learning, well before I started my PhD, I have always found it extremely annoying to keep track of experiments, parameters, and minor variations of code that may or may not be of utmost importance to the success of your project.
This gets incredibly uglier as you wander into uncharted territory, when best practices start to fail you (or have never been defined at all) and the amount of details to keep in mind becomes quickly overwhelming.
However, nothing increases the entropy of a project like introducing new people into the equation, each one with a different skillset, coding style, and amount of experience.

In this post I’ll try to sum up some of the problems that I have encountered when doing ML projects in teams (both for research and competitions), and some of the things that have helped me make my life easier when working on a ML project in general.