Graphs are flexible mathematical objects that can represent many entities and knowledge
from different domains, including in the life sciences. Graph neural networks (GNNs) are …

In many ways, graphs are the main modality of data we receive from nature. This is due to
the fact that most of the patterns we see, both in natural and artificial systems, are elegantly …

Abstract Machine learning plays an increasingly important role in many areas of chemistry
and materials science, being used to predict materials properties, accelerate simulations …

Node features of graph neural networks (GNNs) tend to become more similar with the
increase of the network depth. This effect is known as over-smoothing, which we …

We propose a recipe on how to build a general, powerful, scalable (GPS) graph Transformer
with linear complexity and state-of-the-art results on a diverse set of benchmarks. Graph …

Graph neural networks have been extensively studied for learning with interconnected data.
Despite this, recent evidence has revealed GNNs' deficiencies related to over-squashing …

Abstract Message Passing Neural Networks (MPNNs) are instances of Graph Neural
Networks that leverage the graph to send messages over the edges. This inductive bias …

Recently, transformer architectures for graphs emerged as an alternative to established
techniques for machine learning with graphs, such as (message-passing) graph neural …

Graph representation learning aims to effectively encode high-dimensional sparse graph-
structured data into low-dimensional dense vectors, which is a fundamental task that has …

Transformers for graph data are increasingly widely studied and successful in numerous
learning tasks. Graph inductive biases are crucial for Graph Transformers, and previous …