Standardized entity representation learning for smart suggestions

1. A system comprising:

one or more computer processors; and

a computer-readable medium having instructions stored thereon, which, when executed by the one or more processors, cause the system to:

retrieve an indication of a plurality of different entities in a social networking service, including at least two entities having a different entity type, each entity type being a different category of entities;

access a plurality of user profiles in the social networking service;

generate a heterogeneous graph structure comprising a plurality of nodes connected by edges, each node corresponding to a different one of the entities in the plurality of different entities, each edge representing a co-occurrence of entities represented by nodes on each side of the edge in at least one of the user profiles;

compute weights for each edge of the heterogeneous graph structure, the weights being based on co-occurrence counts reflecting a number of user profiles in the plurality of user profiles in which corresponding nodes co-occurred;

embed the heterogeneous graph structure into a d-dimensional space, d being a number of dimensions;

use a machine-learned model to calculate a similarity score between a first node and a second node from the plurality of nodes by computing a distance between the first node and the second node in the d-dimensional space; and

use the similarity score to determine an entity to display on a computing device.

2. The system of claim 1 , wherein the indication is a standardized entity taxonomy.

3. The system of claim 1 , wherein the first node corresponds to an entity contained in a first user profile returned to a first user in response to a first query, and the instructions further cause the system to:

determine that the second node corresponds to an entity to recommend to the first user in response to the first query based on the calculated similarity score; and

present the second node as a recommended addition to the first query.

4. The system of claim 3 , wherein the presenting of the second node includes displaying the entity corresponding to the second node as a selectable facet in a graphical user interface displaying the first user profile as a search result for the first query.

5. The system of claim 3 , wherein the presenting of the second node includes displaying the entity corresponding to the second node as an added search term available for query augmentation in a graphical user interface displaying the first user profile as a search result for the first query.

6. The system of claim 1 , wherein the machine-learned model is an unsupervised machine-learned model.

7. The system of claim 1 , wherein the instructions further cause the system to:

eliminate any nodes from the heterogeneous graph structure that correspond to entities having a co-occurrence count with any other nodes in the heterogeneous graph structure less than a preset threshold.

8. A computer-implemented method, comprising:

retrieving an indication of a plurality of different entities in a social networking service, including at least two entities having a different entity type, each entity type being a different category of entities;

accessing a plurality of user profiles in the social networking service;

generating a heterogeneous graph structure comprising a plurality of nodes connected by edges, each node corresponding to a different one of the entities in the plurality of different entities, each edge representing a co-occurrence of entities represented by nodes on each side of the edge in at least one of the user profiles;

computing weights for each edge of the heterogeneous graph structure, the weights being based on co-occurrence counts reflecting a number of user profiles in the plurality of user profiles in which corresponding nodes co-occurred;

embedding the heterogeneous graph structure into a d-dimensional space, d being a number of dimensions;

using a machine-learned model to calculate a similarity score between a first node and a second node by computing a distance between the first node and the second node in the d-dimensional space; and

using the similarity score to determine an entity to display on a computing device.

9. The method of claim 8 , wherein the indication is a standardized entity taxonomy.

10. The method of claim 8 , wherein the first node corresponds to an entity contained in a first user profile returned to a first user in response to a first query, and the method further comprises:

determining that the second node corresponds to an entity to recommend to the first user in response to the first query based on the calculated similarity score; and

presenting the second node as a recommended addition to the first query.

11. The method of claim 10 , wherein the presenting of the second node includes displaying the entity corresponding to the second node as a selectable facet in a graphical user interface displaying the first user profile as a search result for the first query.

12. The method of claim 10 , wherein the presenting of the second node includes displaying the entity corresponding to the second node as an added search term available for query augmentation in a graphical user interface displaying the first user profile as a search result for the first query.

13. The method of claim 8 , wherein the machine-learned model is an unsupervised machine-learned model.

14. The method of claim 8 , further comprising:

eliminating any nodes from the heterogeneous graph structure that correspond to entities having a co-occurrence count with any other nodes in the heterogeneous graph structure less than a preset threshold.

15. A non-transitory machine-readable storage medium comprising instructions, which when implemented by one or more machines, cause the one or more machines to perform operations comprising:

retrieving an indication of a plurality of different entities in a social networking service, including at least two entities having a different entity type, each entity type being a different category of entities;

accessing a plurality of user profiles in the social networking service;

generating a heterogeneous graph structure comprising a plurality of nodes connected by edges, each node corresponding to a different one of the entities in the plurality of different entities, each edge representing a co-occurrence of entities represented by nodes on each side of the edge in at least one of the user profiles;

computing weights for each edge of the heterogeneous graph structure, the weights being based on co-occurrence counts reflecting a number of user profiles in the plurality of user profiles in which corresponding nodes co-occurred;

embedding the heterogeneous graph structure into a d-dimensional space, d being a number of dimensions;

using a machine-learned model to calculate a similarity score between a first node and a second node by computing a distance between the first node and the second node in the d-dimensional space; and

using the similarity score to determine an entity to display on a computing device.

16. The non-transitory machine-readable storage medium of claim 15 , wherein the indication is a standardized entity taxonomy.

17. The non-transitory machine-readable storage medium of claim 15 , wherein the first node corresponds to an entity contained in a first user profile returned to a first user in response to a first query, and the instructions further comprise:

determining that the second node corresponds to an entity to recommend to the first user in response to the first query based on the calculated similarity score; and

presenting the second node as a recommended addition to the first query.

18. The non-transitory machine-readable storage medium of claim 17 , wherein the presenting of the second node includes displaying the entity corresponding to the second node as a selectable facet in a graphical user interface displaying the first user profile as a search result for the first query.

19. The non-transitory machine-readable storage medium of claim 17 , wherein the presenting of the second node includes displaying the entity corresponding to the second node as an added search term available for query augmentation in a graphical user interface displaying the first user profile as a search result for the first query.

20. The non-transitory machine-readable storage medium of claim 15 , wherein the machine-learned model is an unsupervised machine-learned model.