UPDATING FEATURES BASED ON USER ACTIONS IN ONLINE SYSTEMS

摘要

Online systems, for example, social networking systems store features describing relations between entities represented in the online system. The information describing the features is represented as a graph. The online system maintains a cumulative feature graph and an incremental feature graph. Feature values based on recent user actions are stored in the incremental graph and feature values based on previous actions are stored in the cumulative graph. Periodically, the information stored in the incremental feature graph is merged with the information stored in the cumulative feature graph. The incremental graph is marked as inactive during the merge and information based on new user actions is stored in an active incremental feature graph. If a request for feature information is received, the feature information obtained from the cumulative feature graph, inactive incremental feature graph and the active incremental feature graph are combined to determine the feature information.

主权项

1. A computer-implemented method comprising:
maintaining, by an online system, a cumulative feature graph and a plurality of incremental feature graphs, the cumulative feature graph and each of the plurality of incremental feature graphs storing feature information describing features, each feature associated with a source entity represented in the online system, a target entity represented in the online system, and a feature value based on interactions between the source entity and the target entity; and updating the cumulative feature graph based on the plurality of incremental feature graphs by:
merging first feature values of a first incremental feature graph from the plurality of incremental feature graphs with cumulative feature values of the cumulative feature graph; andupdating a second incremental feature graph from the plurality of incremental feature graphs to store second feature values describing interactions with entities of the online system occurring while the first feature values of the first incremental feature graph are merged with the cumulative feature values of the cumulative feature graph.