Babylon Partners Limited

Iqvia Inc.

Daniel William Busbridge

Nils Yannick Hammerla

Pietro Cavallo

Dane Grant Sherburn

Gwyn Rhys Jones

Peter Paul Riebel

A graphical classification method for classifying graphical structures, said graphical structures comprising nodes defined by feature vectors and having relations between the nodes. The method includes representing the feature vectors and relations as a first graphical representation. The method also includes mapping said first graphical representation into a second graphical representation wherein the mapping comprises using an attention mechanism, said attention mechanism establishes the importance of specific feature vectors dependent on their neighbourhood and the relations between the feature vectors, said mapping transforming the feature vectors of the first graphical representation to transformed feature vectors in the second graphical representation. The method also includes combining the transformed feature vectors to obtain a third combined representation said third combined representation being an indication of the classification of the graphical structure.

Method and system for extracting information from graphs

A computer-implemented method includes a computing system having a database that stores multiple datasets and that accesses the database to perform operations on a first dataset to produce multiple second datasets. The system determines a relationship between the first dataset and each second dataset of the multiple second datasets. The system also determines a relationship between respective groups of the first dataset and determines a relationship between respective groups of each second dataset. The system generates summary objects based, in part, on the determined relationships between respective groups of the first and second datasets. The system includes a machine learning system that uses the respective summary objects to analyze the performed operations that produced the multiple second datasets. Based on the analyzed performed operations, the machine learning system generates a data analysis model that indicates sequences of operations for achieving particular desired data analysis outcomes.

System and method for enhanced characterization of structured data for machine learning

A computer implemented method for classifying molecular structures is provided. The method includes representing the elements and atoms in a molecular structure as nodes and the bonds as relations as a first graphical representation. The method also includes mapping said first graphical representation into a second graphical representation wherein the mapping comprises using an attention mechanism, said attention mechanism establishes the importance of specific feature vectors dependent on their neighbourhood and the relations between the feature vectors, said mapping transforming the feature vectors of the first graphical representation to transformed feature vectors in the second graphical representation. The method also includes combining the transformed feature vectors to obtain a third combined representation. The method also includes mapping said third combined representation to a feature vector indicating properties of the molecular structure.

A method of training a model, said model being adapted to map a first graphical data structure representation to a second graphical data structure representation, the first graphical data structure representation comprising nodes, with at least one of a plurality of relations between said nodes, the second graphical data structure representation comprising nodes, the mapping comprises using an attention mechanism, wherein said attention mechanism establishes the importance of specific nodes dependent on their neighbourhood and the relations between the nodes, wherein the mapping comprising using a projection kernel to map the nodes of the first graphical structure to nodes of an intermediate representation and using an attention kernel to enact the attention mechanism. The method includes receiving a training data set comprising an output layer and a corresponding input layer. The method also includes training the parameters of the projection kernel and the attention kernel using the training data set.

A method of mapping a first graphical data structure representation to a second graphical data structure representation, the first graphical data structure representation comprising nodes, with at least one of a plurality of relations between said nodes, the second graphical data structure representation comprising nodes, the mapping comprises using an attention mechanism, wherein said attention mechanism establishes the importance of specific nodes dependent on their neighbourhood and the relations between the nodes.

Growing community of inventors

London, United Kingdom

Daniel William Busbridge