Abstract: Embodiments of the disclosed technologies include identifying a user of a network as a possible contributor of digital content to a document that is published via the network; identifying at least two different channels on the network that are each capable of sending, to the user, an invitation for the user to contribute to the document; for each of the at least two different channels, determining respective channel usage data, where the channel usage data includes, for a channel of the at least two different channels, historical data relating to use of the channel by the user to interact with content; for each of the at least two different channels, computing respective channel affinity scores based on the respective channel usage data, where a channel affinity score includes, for a channel of the at least two different channels, an estimate of a likelihood of the user contributing to the document through the channel; based on the respective channel affinity scores, selecting an optimal channel from the at l

Abstract: In an example embodiment, a deep learning model is used to learn embedding representations of a heterogeneous information network, where the embedding represents entity-specific properties and network environment properties. Position-aware embeddings specific to the heterogeneous information network may be used as input features of the deep learning model. Furthermore, meta-path embedding specific to the heterogeneous information network may also be used as input features of the deep learning model. Modified embedding propagation methods are further designed to explore better ways to capture network meta-path properties.

Abstract: In an example embodiment, a deep learning model is used to learn embedding representations of a heterogeneous information network, where the embedding represents entity-specific properties and network environment properties. Position-aware embeddings specific to the heterogeneous information network may be used as input features of the deep learning model. Furthermore, meta-path embedding specific to the heterogeneous information network may also be used as input features of the deep learning model. Modified embedding propagation methods are further designed to explore better ways to capture network meta-path properties.

Abstract: Techniques for generating training data to capture entity-to-entity affinities are provided. In one technique, first interaction data is stored that indicates interactions, that occurred during a first time period, between a first set of users and content items associated with a first set of entities. Also, second interaction data is stored that indicates interactions, that occurred during a second time period, between a second set of users and content items associated with a second set of entities. For each interaction in the first interaction data: (1) a training instance is generated; (2) it is determined whether the interaction matches one in the second interaction data; and (3) if the interaction does not match, then a negative label is generated for the training instance, else a positive label is generated for the training instance. Machine learning techniques are then used to train a machine-learned model based on the generating training instances.