Our research focuses on graph machine learning, non-stationary environments, dynamical systems, and reinforcement learning.
We also apply machine learning in many diverse fields, including neuroscience, power grids, chemistry, and agriculture, among many others.
Our group is active in open source software development and we maintain several Python libraries based on our research.
A library for building graph neural networks in Keras and Tensorflow.
A Python library for detecting changes in stationarity in sequences of graphs.
A Keras library that provides multiple deep architectures for multi-step time-series forecasting.
The development of Spektral and CDG was supported by project ALPSFORT (200021 172671) of the Swiss National Science Foundation.