By one of the most fundamental principles in physics, a dynamical system will exhibit those motions which extremise an action functional.
In this paper we study the practicality and usefulness of incorporating distributed representations of graphs into models within the context of drug pair scoring.
Active learning (AL) is a sub-field of ML focused on the development of methods to iteratively and economically acquire data through strategically querying new data points that are the most useful for a particular task.
4 code implementations • 15 Apr 2021 • Benedek Rozemberczki, Paul Scherer, Yixuan He, George Panagopoulos, Alexander Riedel, Maria Astefanoaei, Oliver Kiss, Ferenc Beres, Guzmán López, Nicolas Collignon, Rik Sarkar
We present PyTorch Geometric Temporal a deep learning framework combining state-of-the-art machine learning algorithms for neural spatiotemporal signal processing.
Recurrent graph convolutional neural networks are highly effective machine learning techniques for spatiotemporal signal processing.
Stratifying cancer patients based on their gene expression levels allows improving diagnosis, survival analysis and treatment planning.
We propose a method for gene expression based analysis of cancer phenotypes incorporating network biology knowledge through unsupervised construction of computational graphs.
We present Geo2DR (Geometric to Distributed Representations), a GPU ready Python library for unsupervised learning on graph-structured data using discrete substructure patterns and neural language models.
We present two instances, L-GAE and L-VGAE, of the variational graph auto-encoding family (VGAE) based on separating feature propagation operations from graph convolution layers typically found in graph learning methods to a single linear matrix computation made prior to input in standard auto-encoder architectures.