Microsoft Technology Licensing, LLC

Linkedin Corporation

Xiaowen Zhang

Qing Duan

Xiaoqing Wang

Angela Yoonjeong Yang

Samaneh Abbasi Moghaddam

Lawrence Yuan

Chanh Nguyen

Junrui Xu

Stephane Dahan

Aman Grover

Benjamin Hoan Le

Girish Kathalagiri Somashekariah

SeyedMohsen Jamali

In an example embodiment, a skip logic using downsampling is applied to negative signals on a training data set fed to a machine-learning algorithm to train a machine-learned model. By downsampling the negatively labeled pieces of training data, the technical problem encountered in biasing the machine-learned model towards negative cases is overcome.

Down-sampling of negative signals used in training machine-learned model

The disclosed embodiments provide a system for processing data. During operation, the system performs processing related to a first set of features for a first entity using a first series of embedding layers, wherein the processing includes applying each embedding layer in the first series of embedding layers to a concatenation of all outputs of one or more layers preceding the embedding layer. Next, the system obtains a first embedding as an output of a first final layer in the first series of embedding layers. The system then outputs the first embedding for use by a machine learning model.

Entity pyramid embeddings

Technologies for generating a graph containing clusters of feature attribute values for training a machine learning model for content item selection and delivery are provided. The disclosed techniques include, for each entity, of a plurality of entities, a system identifies transitions from one geographic location to another geographic location. A graph is generated based on the transitions associated with each entity. The graph comprises nodes representing geographic locations and edges connecting the nodes. Each of the edges connects two nodes, represents a transition from one geographic location to another geographic location, and each edge represents an edge weight value that is based on frequencies of transitions between geographic locations represented by the two connected nodes. The system generates a plurality of clusters from the nodes based upon the edge weight value of each edge. The system includes the plurality of clusters as features in a machine learning model.

Location dimension reduction using graph techniques

In an example embodiment, cohort-based generalized linear mixed effect model (GLMIX) training is performed to identify patterns across cohorts of users, rather than slicing across all users blindly without accounting for common characteristics of users. Thus, rather than performing GLMIX training at just the finest granular level (e.g., user-level and job-level) or the highest level (global level), a 'medium' level of granularity is used to train the GLMIX model at cohort-level.

Cohort-based generalized linear mixed effect model

In an example the output of a machine learned model is a score is then compared to a threshold, and if the score transgresses the threshold, the corresponding item is available to be recommended to the user via the graphical user interface. In an example embodiment, rather than a fixed (static) threshold, a dynamic threshold is utilized. This dynamic threshold is based on a harmonic mean of probabilities utilized in the GLMix model. Specifically, the GLMix model may calculate and utilize the probability that a user will engage with a particular item via a graphical user interface, and also a probability that a user will dismiss a particular item via a graphical user interface.

Personalized model threshold

Methods and systems of providing a guided navigation experience are described. According to various embodiments, a first type of use case may be determined for a first use of a website by a user. The first type of use case may be determined amongst a plurality of types of use cases. A first navigation recommendation may be determined based on the determined first type of use case. The first navigation recommendation may comprise a recommendation for the user to navigate to a first content on the website. The first navigation recommendation may be caused to be displayed to the user. In some embodiments, the plurality of types of use cases may comprise at least one of viewing an update of a profile of another user, viewing an event associated with the profile of another user, performing a job search, and participating in or viewing a discussion.

Growing community of inventors

San Francisco, CA, United States of America

Xiaowen Zhang