Method and system for extracting information from graphs

1. A computer-implemented graphical classification method for classifying graphical data structures, said graphical data structures comprising nodes defined by feature vectors and having relations between the nodes, the method comprising:

representing the feature vectors and the relations as a first graphical data structure representation;

mapping said first data structure graphical representation into a second graphical data structure representation, wherein the mapping comprises using an attention mechanism, said attention mechanism establishing an 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 data structure representation to transformed feature vectors in the second graphical data structure representation; and

combining the transformed feature vectors to obtain a third combined graphical data structure representation said third combined graphical data structure representation being an indication of a classification of a graphical structure.

2. The method of claim 1 , wherein the attention mechanism is enacted by attention coefficients and there is a coupling between the attention coefficients across different relations.

3. The method of claim 1 , wherein the attention mechanism is enacted by attention coefficients and the attention coefficients across a neighbourhood are normalised.

4. The method of claim 1 , wherein the attention mechanism is enacted by attention coefficients and the attention coefficients across a neighbourhood of nodes for one relation are normalised.

5. The method of claim 1 , wherein the nodes of the first graphical data structure representation each comprise a feature vector and the nodes of the second graphical data structure representation also each comprise a feature vector, the mapping converting features of the feature vectors of the first graphical data structure representation into the transformed feature vectors of the second graphical data structure representation.

6. The method of claim 5 , wherein the feature vectors of the first graphical data structure representation are transformed into feature vectors of the second graphical data structure representation via a linear transformation and the attention mechanism.

7. The method of claim 6 , wherein the attention mechanism is configured such that, after the linear transformation, the relations between the linearly transformed feature vectors of the second graphical data structure representation are independent of other relations.

8. The method of claim 7 , wherein the attention mechanism comprises attention coefficients derived from a product of a relation dependent vector with a concatenation of two related nodes where feature vectors from the two related nodes have been transformed via said linear transformation.

9. The method of claim 8 , wherein the attention coefficients are derived from the product using an activation function that allows normalisation over a neighbourhood of nodes.

10. The method of claim 6 , wherein matrices that define the linear transformation and the attention mechanism are decomposed.

11. The method of claim 1 , where the attention mechanism is a multi-head attention mechanism.

12. A system for classifying graphical data structures, said graphical data structures comprising nodes defined by feature vectors and having relations between the nodes, said system comprising a processor and a memory, the processor being configured to:

represent the feature vectors and the relations as a first graphical data structure representation;

map said first graphical data structure representation into a second graphical data structure representation, wherein the mapping comprises using an attention mechanism, said attention mechanism establishing an 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 data structure representation to transformed feature vectors in the second graphical data structure representation; and

combine the transformed feature vectors to obtain a third combined graphical data structure representation, said third combined graphical data structure representation being an indication of a classification of a graphical structure.

13. The system of claim 12 , wherein the processor comprises a GPU.

14. A non-transitory carrier medium comprising computer readable instructions, which, when executed on a computer, cause the computer to perform a graphical classification method for classifying graphical data structures, said graphical data structures comprising nodes defined by feature vectors and having relations between the nodes, the method comprising:

representing the feature vectors and the relations as a first graphical data structure representation;

mapping said first graphical data structure representation into a second graphical data structure representation, wherein the mapping comprises using an attention mechanism, said attention mechanism establishing an 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 data structure representation; and

combining the transformed feature vectors to obtain a third combined graphical data structure representation said third combined graphical data structure representation being an indication of a classification of a graphical structure.