Node embedding in multi-view feature vectors

1. A system comprising:

a processor; and

memory coupled to the processor and storing instructions that, when executed by the processor, cause the system to perform operations comprising:

retrieving electronic content from a database in communication with the system;

identifying a plurality of nodes within the electronic content, each respective node in the plurality of nodes comprising a respective portion of the electronic content;

identifying a plurality of views associated with the electronic content, wherein each respective view is associated with a respective portion of the plurality of nodes, and wherein at least a subset of the plurality of nodes is common to at least two of the views in the plurality of views;

generating a respective sequence of nodes for each respective view in the plurality of views;

for each respective view, traversing each respective node in the respective sequence of nodes for the respective view to determine a respective embedding for the respective node for the respective view; and

determining, based on the determined embedding for each respective node in the plurality of nodes, a respective view-independent embedding for the respective node.

2. The system of claim 1 , wherein the electronic content includes one or more of: text, an image, audio, and video.

3. The system of claim 1 , wherein traversing each respective node includes sampling a node adjacent to the respective node in the respective sequence of nodes for the respective view.

4. The system of claim 3 , wherein traversing each respective node includes sampling a predetermined number of negative samples of nodes, relative to the respective node, in the respective sequence of nodes.

5. The system of claim 4 , wherein traversing each respective node includes performing a one-step gradient descent for the respective node based on the sampled adjacent node and the predetermined number of negative samples of nodes.

6. The system of claim 5 , wherein the one-step gradient descent updates a direction of an embedding vector associated with the respective node.

7. The system of claim 6 , wherein a magnitude of the direction updated to the embedding vector is based on a gradient length.

8. The system of claim 6 , wherein determining the respective view-independent embedding for each respective node includes concatenating the embedding vectors from the plurality of views for the respective node.

9. The system of claim 1 , wherein determining the respective embedding for the respective nodes for each respective view includes identifying, for each respective view, a set of edges between the respective nodes in the respective view, each edge in the set of edges denoting a relationship between a pair of nodes in the respective view.

10. The system of claim 9 , wherein each respective view in the plurality of views comprises edges associated with a respective time frame.

11. The system of claim 9 , wherein each respective node is associated with a respective phrase contained within the electronic content.

12. The system of claim 11 , wherein an edge between a first node and a second node in a view from the plurality of views denotes a phrase associated with the first node and a phrase associated with the second node are both present in a portion of the electronic content.

13. The system of claim 9 , wherein each respective node is associated with a respective user of an online social network described within the electronic content.

14. The system of claim 13 , wherein an edge between a first node and a second node in a view from the plurality of views denotes a connection in the online social network between a first user associated with the first node and a second user associated with the second node.

15. The system of claim 1 , wherein the plurality of nodes are common to all views in the plurality of views.

16. The system of claim 1 , wherein generating the respective sequence of nodes for each respective view includes performing a plurality of random recursive traversals of the plurality of nodes for the respective view.

17. The system of claim 1 , wherein determining the respective embedding for each respective node includes initializing an embedding entry based on a uniform sampling of a value associated with the plurality of nodes.

18. The system of claim 1 , wherein determining the respective embedding for each respective node includes initializing an embedding entry using a predetermined value.

19. A method comprising:

retrieving, by a computer system, electronic content from a database in communication with the computer system;

identifying, by the computer system, a plurality of nodes within the electronic content, each respective node in the plurality of nodes comprising a respective portion of the electronic content;

identifying, by the computer system, a plurality of views associated with the electronic content, wherein each respective view is associated with a respective portion of the plurality of nodes, and wherein at least a subset of the plurality of nodes is common to at least two of the views in the plurality of views;

generating, by the computer system, a respective sequence of nodes for each respective view in the plurality of views;

for each respective view, traversing, by the computer system, each respective node in the respective sequence of nodes for the respective view to determine a respective embedding for the respective node for the respective view; and

determining, by the computer system and based on the determined embedding for each respective node in the plurality of nodes, a respective view-independent embedding for the respective node.

20. A non-transitory computer-readable medium storing instructions that, when executed by a computer system, cause the computer system to perform operations comprising:

retrieving electronic content from a database in communication with the system;

identifying a plurality of nodes within the electronic content, each respective node in the plurality of nodes comprising a respective portion of the electronic content;

identifying a plurality of views associated with the electronic content, wherein each respective view is associated with a respective portion of the plurality of nodes, and wherein at least a subset of the plurality of nodes is common to at least two of the views in the plurality of views;

generating a respective sequence of nodes for each respective view in the plurality of views;

for each respective view, traversing each respective node in the respective sequence of nodes for the respective view to determine a respective embedding for the respective node for the respective view; and

determining, based on the determined embedding for each respective node in the plurality of nodes, a respective view-independent embedding for the respective node.