Hybrid graph neural network
An embodiment includes extracting, responsive to an update request from a remote requesting system, technical descriptor data from a data source. The embodiment also includes forming a new graph data structure using the technical descriptor data extracted from the data source. The embodiment also includes augmenting the new graph data structure to include a concept based on a value from instance data from the data source. The embodiment also includes identifying a first pair of concepts that are connected in a pre-existing ontology that correspond with a second pair of concepts that lack a connection therebetween in the new graph structure. The embodiment also includes augmenting the new graph data structure to include a connection between the second pair of concepts. The embodiment also includes outputting the new graph data structure as part of a response to the update request from the requesting system.
1. A computer implemented method comprising:
extracting, responsive to an update request from a remote requesting system, technical descriptor data from a data source, wherein the technical descriptor data describes a construct of a data structure of the data source;
forming a new graph data structure using the technical descriptor data extracted from the data source, wherein the forming the new graph data structure comprises projecting node embeddings into a hyperbolic space representation that captures hierarchical and non-hierarchical connections between concepts;
augmenting the new graph data structure to include a concept based on a value from instance data from the data source;
identifying a first pair of concepts that are connected in a pre-existing ontology that correspond with a second pair of concepts that lack a connection therebetween in the new graph structure, wherein the identifying the first pair of concepts that are connected in the pre-existing ontology comprises identifying a hierarchical connection between concepts of the first pair of concepts, and a non-hierarchical connection between concepts of the first pair of concepts;
identifying a top-level concept that is connected to the first pair of concepts in the pre-existing ontology;
augmenting the new graph data structure to include a connection between the second pair of concepts, wherein the augmenting the new graph data is based at least in part on the hierarchical connection between concepts of the first pair of concepts, the non-hierarchical connection between concepts of the first pair of concepts, and the top-level concept that is connected to the first pair of concepts in the pre-existing ontology; and
outputting the new graph data structure as part of a response to the update request from the requesting system.
2. The method of claim 1 , wherein the technical descriptor data comprises technical metadata.
3. The method of claim 1 , wherein the data source comprises a relational database.
4. The method of claim 1 , wherein the technical descriptor data comprises schema level data.
5. The method of claim 4 , wherein the forming of the new graph data structure using the technical descriptor data comprises adding schema level nodes corresponding to respective schema values of the schema level data.
6. The method of claim 5 , wherein the augmenting of the new graph data structure to include the concept further comprises identifying each distinct value in the instance data of the data source.
7. The method of claim 6 , wherein the augmenting of the new graph data structure to include the concept further comprises adding, for each distinct value identified in the instance data of the data source, an instance concept connected to a respective one of the schema level nodes.
8. The method of claim 1 , wherein the new graph structure comprises a new ontology.
9. The method of claim 8 , further comprising updating the new ontology using an OntoGNN.
10. The method of claim 9 , wherein the updating of the new ontology comprises using the new ontology as a source ontology for the OntoGNN and using the pre-existing ontology as a target ontology for the OntoGNN.
11. The method of claim 10 , wherein the updating of the new ontology using the OntoGNN comprises:
generating a first concept representation based on a first portion of the new ontology using a first processing path of the OntoGNN, the first processing path comprising a first hyperbolic graph convolution layer, the first portion of the new ontology comprising a first key concept;
generating a second concept representation based on a second portion of the new ontology using a second processing path of the OntoGNN, the second processing path comprising a first heterogenous graph convolution layer, the second portion of the new ontology comprising the first key concept;
generating a first unified concept representation including concatenating the first concept representation with the second concept representation; and
generating a prediction score using a predictive matching module, the predictive score being indicative of an extent of a match between the first unified concept representation and a second unified concept representation from the pre-existing ontology.
12. A computer usable program product for cognitive analysis of a project description, the computer program product comprising one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable by a processor to cause the processor to perform operations comprising:
extracting, responsive to an update request from a remote requesting system, technical descriptor data from a data source, wherein the technical descriptor data describes a construct of a data structure of the data source;
forming a new graph data structure using the technical descriptor data extracted from the data source;
augmenting the new graph data structure to include a concept based on a value from instance data from the data source;
identifying a top-level concept that is connected to the first pair of concepts in the pre-existing ontology;
identifying a first pair of concepts that are connected in a pre-existing ontology that correspond with a second pair of concepts that lack a connection therebetween in the new graph structure;
augmenting the new graph data structure to include a connection between the second pair of concepts wherein the augmenting the new graph data is based at least in part on a connection between concepts of the first pair of concepts, and a connection between the top-level concept that is connected to the first pair of concepts in the pre-existing ontology; and
outputting the new graph data structure as part of a response to the update request from the requesting system.
13. The computer usable program product of claim 12 , wherein the stored program instructions are stored in a computer readable storage device in a data processing system, and wherein the stored program instructions are transferred over a network from a remote data processing system.
14. The computer usable program product of claim 12 , wherein the stored program instructions are stored in a computer readable storage device in a server data processing system, and wherein the stored program instructions are downloaded in response to a request over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system, further comprising:
program instructions to meter use of the computer usable code associated with the request; and
program instructions to generate an invoice based on the metered use.
15. The computer usable program product of claim 12 , wherein the technical descriptor data comprises technical metadata.
16. The computer usable program product of claim 12 , wherein the data source comprises a relational database.
17. The computer usable program product of claim 12 , wherein the technical descriptor data comprises schema level data.
18. A computer system comprising a processor and one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable by the processor to cause the processor to perform operations comprising:
extracting, responsive to an update request from a remote requesting system, technical descriptor data from a data source, wherein the technical descriptor data describes a construct of a data structure of the data source;
forming a new graph data structure using the technical descriptor data extracted from the data source, wherein the forming the new graph data structure comprises projecting node embeddings into a hyperbolic space representation that captures hierarchical and non-hierarchical connections between concepts;
augmenting the new graph data structure to include a concept based on a value from instance data from the data source;
identifying a first pair of concepts that are connected in a pre-existing ontology that correspond with a second pair of concepts that lack a connection therebetween in the new graph structure, wherein the identifying the first pair of concepts that are connected in the pre-existing ontology comprises identifying a hierarchical connection between concepts of the first pair of concepts, and a non-hierarchical connection between concepts of the first pair of concepts;
identifying a top-level concept that is connected to the first pair of concepts in the pre-existing ontology;
augmenting the new graph data structure to include a connection between the second pair of concepts, wherein the augmenting the new graph data is based at least in part on the hierarchical connection between concepts of the first pair of concepts, the non-hierarchical connection between concepts of the first pair of concepts, and the top-level concept that is connected to the first pair of concepts in the pre-existing ontology; and
outputting the new graph data structure as part of a response to the update request from the requesting system.
19. The computer system of claim 18 , wherein the technical descriptor data comprises technical metadata.
20. The computer system of claim 18 , wherein the data source comprises a relational database.