Deep graph representation learning
View Patent ↗A method of deep graph representation learning includes: deriving a set of base features; and automatically developing, by a processing device, a multi-layered hierarchical graph representation based on the set of base features, wherein each successive layer of the multi-layered hierarchical graph representation leverages an output from a previous layer to learn features of a higher-order.
1. A method of deep graph representation learning, the method comprising:
deriving a set of base features;
adding the set of base features to a feature matrix;
generating, by a processing device, a current feature layer from the feature matrix, the current feature layer corresponding to a set of current features;
selecting a subset of features from the set of current features based on an evaluation of the set of current features; and
adding the subset of features to the feature matrix to generate an updated feature matrix.
2. The method of claim 1 , wherein the evaluation of the set of current features comprises:
evaluating feature pairs associated with the current feature layer.
3. The method of claim 1 , further comprising:
incrementing the current feature layer to generate a new current feature layer.
4. The method of claim 1 , further comprising:
transforming the set of base features after generating a current feature layer to generate a plurality of transformed based features; and
adding the plurality of transformed base features to the updated feature matrix to generate a new updated feature matrix.
5. The method of claim 1 , further comprising:
transforming the set of current features after generating a current feature layer.
6. The method of claim 1 , wherein a plurality of features in the feature matrix are transfer learning features.
7. The method of claim 1 , wherein selecting the subset of features further comprises:
applying a set of relational feature operators to each feature of a previous feature layer.
8. A system comprising:
a memory to store a set of base features; and
a processing device, operatively coupled to the memory, to:
derive the set of base features;
add the set of base features to a feature matrix;
generate a current feature layer from the feature matrix, the current feature layer corresponding to a set of current features;
select a subset of features from the set of current features based on an evaluation of the set of current features; and
add the subset of features to the feature matrix to generate an updated feature matrix.
9. The system of claim 8 , wherein to evaluate the set of current features the processing device is further to:
evaluate feature pairs associated with the current feature layer.
10. The system of claim 8 , wherein the processing device is further to:
increment the current feature layer to generate a new current feature layer.
11. The system of claim 8 , wherein the processing device is further to:
transform the set of base features after generating a current feature layer to generate a plurality of transformed based features; and
add the plurality of transformed base features to the updated feature matrix to generate a new updated feature matrix.
12. The system of claim 8 , wherein the processing device is further to:
transform the set of current features after generating a current feature layer.
13. The system of claim 8 , wherein the processing device is one or more graphics processing units of one or more servers.
14. The system of claim 8 , wherein to select the subset of features the processing device is to:
apply a set of relational feature operators to each feature of a previous feature layer.
15. A non-transitory computer-readable storage medium having instructions stored thereon that, when executed by a processing device, cause the processing device to:
derive a set of base features;
add the set of base features to a feature matrix;
generate, by the processing device, a current feature layer from the feature matrix, the current feature layer corresponding to a set of current features;
select a subset of features from the set of current features based on an evaluation of the set of current features; and
add the subset of features to the feature matrix to generate an updated feature matrix.
16. A non-transitory computer-readable storage medium of claim 15 , wherein to evaluate the set of current features, the processing device further to:
evaluate feature pairs associated with the current feature layer.
17. The non-transitory computer-readable storage medium of claim 15 , the processing device further to:
increment the current feature layer to generate a new current feature layer.
18. The non-transitory computer-readable storage medium of claim 15 , the processing device further to:
transform the set of base features after generating a current feature layer to generate a plurality of transformed based features; and
add the plurality of transformed base features to the updated feature matrix to generate a new updated feature matrix.
19. The non-transitory computer-readable storage medium of claim 15 , the processing device further to:
transform the set of current features after generating a current feature layer.
20. The non-transitory computer-readable storage medium of claim 15 , wherein a plurality of features in the feature matrix are transfer learning features.