I didn’t make it to Punta Cana this year 😢 but I’m happy (remotely) for the folks who managed to get there in spite of all traveling restrictions! Premium content inside. The autumn got very busy and I’d like to try a shorter format: each big topic has one “spotlight” 🛋 work in the main block which I find particularly interesting, and several relevant works which have a bit … [Read more...] about Knowledge Graphs At EMNLP 2021

# Graph Neural Networks

## How To Visualize Databases As Network Graphs In Python

At work I recently faced the challenge of having to analyze the data model of an SQL database consisting of more than 500 tables with thousands of relations. At this scale, the built-in visualization function of phpMyAdmin is insufficient for getting a deep understanding of the structure. What I needed was a tool in which I can apply various filters (e.g., table and … [Read more...] about How To Visualize Databases As Network Graphs In Python

## Graph Convolutional Network Implementation With the PROTEINS Benchmark Dataset

This is part four in a series on graph theory and graph convolutional networks. If you’ve been reading this whole series, you’ve been with me on this entire journey — through discussing what graph theory is and why it matters, what a graph convolutional network even is and how they work, and now we’re here, to the fun part — building our own GCN. If … [Read more...] about Graph Convolutional Network Implementation With the PROTEINS Benchmark Dataset

## What Makes Graph Convolutional Networks Work?

This is the third part of a series on graphs and graph theory in machine learning. By now, if you’ve been following this series, you may have learned a bit about graph theory, why we care about graph structured data in data science, and what the heck a “Graph Convolutional Network” is. Now, I’d like to briefly introduce you to what makes these things work. For my … [Read more...] about What Makes Graph Convolutional Networks Work?

## Graph Convolutional Networks — Explained

In my last article on graph theory, I briefly introduced my latest topic of interest: Graph Convolutional Networks. If you’re here thinking “what do those words mean?”, you’re in the right place. In this article, we’re going to break this topic down, step by step. Part I: What’s This Graph Thing? If this is the first you’re hearing this ‘graph’ word, I’m sorry, but you … [Read more...] about Graph Convolutional Networks — Explained

## Why Graph Theory Is Cooler Than You Thought

What are Graphs? Talk to a scientist in just about any discipline, and ask them the question — based on their discipline — “how does that stuff work?” You’ll likely find that there are systems and networks that you have to consider before you can really understand how any given thing works: whether that’s the human body, a food chain in an ecosystem, a … [Read more...] about Why Graph Theory Is Cooler Than You Thought

## How To Get Started With Graph Machine Learning

This blog is a part of my “deep learning update” series and I want to open it up with a question: What have I learned about Graph ML in 2+ months? Nothing? If that was your first thought, no worries, it’s probably true. 😅 (Bad) jokes aside, my “relative knowledge” (the knowledge I “possess” vs the knowledge I’m aware of) is asymptotically … [Read more...] about How To Get Started With Graph Machine Learning

## Graph Neural Networks for Multi-Relational Data

This article describes how to extend the simplest formulation of Graph Neural Networks (GNNs) to encode the structure of multi-relational data, such as Knowledge Graphs (KGs). The article includes 4 main sections: an introduction to the key idea of multi-relational data, which describes the peculiarity of KGs;a summary of the standard components included in a GNN … [Read more...] about Graph Neural Networks for Multi-Relational Data

## Graph Attention Networks Under the Hood

Graph Neural Networks (GNNs) have emerged as the standard toolbox to learn from graph data. GNNs are able to drive improvements for high-impact problems in different fields, such as content recommendation or drug discovery. Unlike other types of data such as images, learning from graph data requires specific methods. As defined by Michael Bronstein: [..] these methods … [Read more...] about Graph Attention Networks Under the Hood

## Top Applications of Graph Neural Networks 2021

At the beginning of the year, I have a feeling that Graph Neural Nets (GNNs) became a buzzword. As a researcher in this field, I feel a little bit proud (at least not ashamed) to say that I work on this. It was not always the case: three years ago when I was talking to my peers, who got busy working on GANs and Transformers, the general impression that they got on me was that I … [Read more...] about Top Applications of Graph Neural Networks 2021