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 tackling delayed user response by modifying training data for machine-learned models are provided. In one technique, a first machine-learned model generates a score based on a set of feature values. A training instance is generated based on the set of feature values. An attribute of the training instance is modified based on the score to generate a modified training instance. The attribute may be an importance weight of the training instance or a label of the training instance. The modified training instance is added to a training data. One or more machine learning techniques are used to train a second machine-learned model based on the training data.

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 single machine learned model that allows for ranking of entities across all of the different combinations of node types and edge types is provided. The solution calibrates the scores from Edge-FPR models to a single scale. Additionally, the solution may utilize a per-edge type multiplicative factor dictated by the true importance of an edge type, which is learned through a counterfactual experimentation process. The solution may additionally optimize on a single, common downstream metric, specifically downstream interactions that can be compared against each other across all combinations of node types and edge types.

Abstract: An online connection server is configured to more accurately predict connections for a viewing member of an online connection network. The online connection server may implement a machine-learning model that uses prior interactions by the viewing member to determine those connections that are likely to lead to more substantial interactions with the viewing member. The machine-learning model may be implemented using a reinforcement learning technique, such as a Deep Q network. The online connection server may further implement a state representation module that generates a state from a graph-based embedding of the viewing member profile, where the state is used to train the machine-learning model and determine an optimal candidate to recommend as a connection for the viewing member.

Abstract: Techniques for using machine learning to leverage deep segment embeddings are provided. In one technique, a set of training data is processed using one or more machine learning techniques to train a neural network and learn an embedding for each segment of multiple segments. In response to receiving a request, multiple elements are identified, such as a source entity that is associated with the request, a source embedding for the source entity, a particular segment with which the source entity is associated, a segment embedding for the particular segment, and multiple target entities. For each target entity, a target embedding is identified and the target embedding, the source embedding, and the segment embedding are input into the neural network to generate output that is associated with the target entity. Based on the output, data about a subset of the target entities is presented on a computing device.

Abstract: Operations for facilitating establishment of connections in an online network are disclosed. A set of connection recommendations for a first entity associated with the online network is accessed. For each connection recommendation in the set of connection recommendations, a ranking value associated with the connection recommendation is accessed, a utility value corresponding to the connection recommendation is determined, and an adjusted the ranking value for the connection recommendation is calculated. The utility value is a two-sided utility value that combines a prediction of a utility of the first entity and a prediction of a utility of a second entity with respect to a key performance indicator. A set of connection recommendations is communicated for presentation in an interactive user interface of a client device associated with the first entity in accordance with the adjusted ranking value of each connection recommendation.

Abstract: Described herein is a technique for generating personalized scores for a cohort of users of an online service, where the scores are for use in ranking connection recommendations, in the context of generating connection recommendations for a user of the online service. The technique involves using a linear programming (LP) problem solver to solve a multi-objective optimization problem formulated to incorporate competing objectives and specific constraints. The technique allows for personalizing recommendations scores, specifically, to ensure that infrequent users are receiving invitations to connect with other users, thereby increasing overall interaction and engagement.

Abstract: The disclosed embodiments provide a system for performing inference. During operation, the system obtains a graph containing nodes representing members of an online system, edges between pairs of nodes, and edge scores representing confidences in a type of relationship between the pairs of nodes. Next, the system performs a set of iterations that propagate a label for the type of relationship from a first subset of edges to remaining edges in the graph, with each iteration updating a probability of the label for an edge between a pair of nodes based on a subset of edge scores for a second subset of edges connected to one or both nodes in the pair and probabilities of the label for the second subset of edges. The system then performs one or more tasks in the online system based on the probability of the label for the edge.

Abstract: Techniques for generating and leveraging heterogenous edges in an online connection network are provided. In one technique, a particular user is identified. The identification may be made in response to a computing device of the particular user requesting data from a particular system. For each entity type of multiple entity types: (1) a set of entities of the entity type is identified based on one or more attributes of the particular user; (2) a ranking of the set of entities is generated based on one or more criteria; and (3) a subset of the set of entities is selected and included in a final set of entities. The final set of entities includes entities from different entity types of the multiple entity types. The final set of entities is transmitted over a computer network to be presented concurrently on a computing device of the particular user.

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.

Abstract: Technologies for scoring and ranking cohorts containing content items using a machine-learned model are provided. The disclosed techniques include a cross-cohort optimization system that stores, within memory, cohort definition criteria for each cohort of a plurality of cohorts. The optimization system, for a particular user, for each cohort, identifies a plurality of content items that belong to the specific cohort based upon the cohort definition criteria. Using a machine-learned model, the optimization system generates a score for the specific cohort with respect to the particular user's intentions. The optimization system generates a ranking for the plurality of cohorts based on the respective scores of each cohort. The optimization system causes the plurality of content items of each cohort to be displayed concurrently on a computing device of the particular user. Display order for the plurality of cohorts is based on the ranking determined for the plurality of cohorts.

Abstract: Operations for facilitating establishment of connections in an online network are disclosed. A set of connection recommendations for a first entity associated with the online network is accessed. For each connection recommendation in the set of connection recommendations, a ranking value associated with the connection recommendation is accessed, a utility value corresponding to the connection recommendation is determined, and an adjusted the ranking value for the connection recommendation is calculated. The utility value is a two-sided utility value that combines a prediction of a utility of the first entity and a prediction of a utility of a second entity with respect to a key performance indicator. A set of connection recommendations is communicated for presentation in an interactive user interface of a client device associated with the first entity in accordance with the adjusted ranking value of each connection recommendation.

Abstract: In an example embodiment, a single machine learned model that allows for ranking of entities across all of the different combinations of node types and edge types is provided. The solution calibrates the scores from Edge-FPR models to a single scale. Additionally, the solution may utilize a per-edge type multiplicative factor dictated by the true importance of an edge type, which is learned through a counterfactual experimentation process. The solution may additionally optimize on a single, common downstream metric, specifically downstream interactions that can be compared against each other across all combinations of node types and edge types.

Abstract: The present invention relates to a nanocarrier peptide sequence (SEQ ID NO: 6 KXPXXXXA/V/GXGNXX; wherein X is selected from amino acid R, K, A or H. The present invention also relates to the method for cellular delivery, by implementing the steps of: complexation of a peptide nanocarrier sequence: KXPXXXXA/V/GXGNXX; where X is selected from amino acid R,K,A and H having SEQ ID NO: 6 with a macromolecule to obtain a complex; and administering the complex to a targeted mammalian or plant cell or tissue.

Abstract: Techniques for tackling delayed user response by modifying training data for machine-learned models are provided. In one technique, a first machine-learned model generates a score based on a set of feature values. A training instance is generated based on the set of feature values. An attribute of the training instance is modified based on the score to generate a modified training instance. The attribute may be an importance weight of the training instance or a label of the training instance. The modified training instance is added to a training data. One or more machine learning techniques are used to train a second machine-learned model based on the training data.

Abstract: Methods, systems, and computer programs are presented for removing bias among users of an online service based on the amount of user's participation in the online service. One method includes operation for pre-training an invite model that provides a first score associated with a user of an online service and for pre-training an adversarial model that provides a second score, the adversarial model having the first score as an input. Further, the method includes training together the invite model and the adversarial model using an adversarial cost function based on the pre-training of the invite model and the adversarial model. The training together is repeated until discrimination of the invite model is below a predetermined threshold. Further, the invite model is utilized to generate the first scores, where the invite model generates the first scores without bias.

Abstract: A cohort service is configured to address the technical problem of providing recommendations to a member of an online connection network system in a manner that alleviates potentially excessive cognitive load associated with presenting recommended entities indiscriminately as a scrollable list. The cohort service is configured to visually surface recommended relevant entities already grouped as cohorts. A cohort is a grouping of entities based on one or more common attributes, such as, e.g., same school, same company, etc. The cohort service is designed to group recommendation results into cohorts at the server side, which increases the liquidity and the relevance of the recommended entities so that the already grouped recommendations can be sent to the client computer system for presentation to a viewer.

Abstract: Techniques for generating and leveraging heterogenous edges in an online connection network are provided. In one technique, a particular user is identified. The identification may be made in response to a computing device of the particular user requesting data from a particular system. For each entity type of multiple entity types: (1) a set of entities of the entity type is identified based on one or more attributes of the particular user; (2) a ranking of the set of entities is generated based on one or more criteria; and (3) a subset of the set of entities is selected and included in a final set of entities. The final set of entities includes entities from different entity types of the multiple entity types. The final set of entities is transmitted over a computer network to be presented concurrently on a computing device of the particular user.

Abstract: An online connection server is configured to more accurately predict connections for a viewing member of an online connection network. The online connection server may implement a machine-learning model that uses prior interactions by the viewing member to determine those connections that are likely to lead to more substantial interactions with the viewing member. The machine-learning model may be implemented using a reinforcement learning technique, such as a Deep Q network. The online connection server may further implement a state representation module that generates a state from a graph-based embedding of the viewing member profile, where the state is used to train the machine-learning model and determine an optimal candidate to recommend as a connection for the viewing member.