Microsoft Technology Licensing, LLC

Linkedin Corporation

Aastha Jain

Parag Agrawal

Vitaly Gordon

Gloria Lau

Nikita Igorevych Lytkin

Aastha Nigam

Yan Wang

Shaunak Chatterjee

Vinodh Jayaram

Jason Andrew Chen

Ankan Saha

Jason Schissel

Ashwin Narasimha Murthy

Bradley Scott Mauney

Ashish Jain

Prachi Gupta

Yafei Wang

Yiou Xiao

Bohong Zhao

Hema Raghavan

Eric Melz

Nick Swartzendruber

Mitul Tiwari

Eric M Lawrence

Saurabh Agarwal

Andrew S Yu

Curtis Wang

Souvik Ghosh

Michael Maczka

Smriti R Ramakrishnan

Myunghwan Kim

Ehud Milo

Shilpa Gupta

Divya Venugopalan

Albert Lingfeng Cui

Peter Chng

Siyuan Gao

Abdulla Mohammad Al-Qawasmeh

David Sung

Zhanglong Liu

Kathryn L Evans

Udi Milo

Usha Seetharaman

Saravanan Arumugam

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.

Deep representation machine learned model for heterogeneous information networks

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.

Tackling delayed user response by modifying training data for machine-learned models

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.

Recommending edges via importance aware machine learned model

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.

Deep reinforcement learning for long term rewards in an online connection network

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.

Deep segment personalization

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.

Recommending network connections by optimizing for two-sided implicit value of an edge

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.

Inference via edge label propagation in networks

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.

Heterogenous edges in an online network for building active online communities

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.

Intent based second pass ranker for ranking aggregates

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.

Cohort service

A system, a machine-readable storage medium storing instructions, and a computer-implemented method are described herein are directed to Future Connection Engine that generates a select pairing of member accounts for a potential social network connection. The Future Connection Engine predicts, according to the prediction model, a first number of subsequent social network connections for a first member account in the select pairing that will occur after establishing the potential social network connection and a second number of subsequent social network connections for a second member account in the select pairing that will occur after establishing the potential social network connection. The Future Connection Engine generates connection recommendations for display to the select pairing based on whether the first and/or the second number of subsequent social network connections satisfies a threshold.

Future connection score of a new connection

Techniques for optimizing a guided edit process for editing a member profile page are described. According to various embodiments, profile edit task information associated with a member of an online social network service is accessed, the profile edit task information identifying one or more candidate profile edit tasks to be performed to update a member profile page of the member. Thereafter, if it is determined that the member recently completed a difficult profile edit task, a difficult candidate profile edit task is identified, and the member is prompted to perform the difficult candidate profile edit task. If it is determined that the member has not recently completed a difficult profile edit task, an easy candidate profile edit task is identified, and the member is prompted to perform the easy candidate profile edit task.

Guided edit optimization

This disclosure relates to systems and methods for identifying members that increase engagement at an online social network. In one example, a method includes retrieving network connectivity and member interaction data for members of an online social networking service that includes a plurality of explicit social networks, building statistical correlations between properties of the respective explicit social networks and interactions between members of the respective explicit social networks, and ranking a set of potential new members for one of the explicit social networks according to the statistical correlations and a statistical likelihood that the new members will increase member interactions with the explicit social network.

Identifying members that increase engagement

A system, device, and method may include a network interface device configured to be communicatively coupled to a user interface. An electronic data storage may be configured to store social network data related to users having accessed a social network content item A processor, coupled to the network interface device and the electronic data storage, may be configured to identify a relationship among at least some of the users, determine a relevance of the relationship to a member of the social network associated with the social network content item based, at least in part, on a social network profile of the member and social network profiles of the users, and cause the network interface device to display, on the user interface, information related to the relationship on the user interface based, at least in part, on the relevance.

System and method for displaying social network analytics

A method and system to suggest keywords to a social network member is described. A suggested keywords system, in one example embodiment, examines phrases that appear in profiles maintained by the on-line social networking system that are similar to the target profile and identifies those words and phrases that are most prominent in these profiles, utilizing a graph-based approach. These most prominent words and phrases may be presented to the target member as suggested keywords to be included in the member's professional summary.

Suggested keywords

Growing community of inventors

Sunnyvale, CA, United States of America

Aastha Jain