Adobe, Inc.

Vijeth Lomada

Haichun Chen

Vidit Bhatia

Anup Bandigadi Rao

Tung Mai

Charles Menguy

Matvey Kapilevich

Margarita Savova

Moumita Sinha

Harleen S Sahni

Lakshmi Shivalingaiah

Liron Goren Snai

Multi-modal machine-learning model training techniques for search are described that overcome conventional challenges and inefficiencies to support real time output, which is not possible in conventional training techniques. In one example, a search system is configured to support multi-modal machine-learning model training. This includes use of a preview mode and an expanded mode. In the preview mode, a preview segment is generated as part of real time training of a machine learning model. In the expanded mode, the preview segment is persisted as an expanded segment that is used to train and utilize an expanded machine-learning model as part of search.

Multi-modal machine-learning model training for search

The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating user embeddings utilizing an interaction-to-vector neural network. For example, a user embeddings system transforms unorganized data of user interactions with content items into structured user interaction data. Further, the user embeddings system can utilize the structured user interaction data to train a neural network in a semi-supervised manner and generate uniform vectorized user embeddings for each of the users.

Generating homogenous user embedding representations from heterogeneous user interaction data using a neural network

The present disclosure relates to systems, non-transitory computer-readable media, and methods for expanding user segments automatically utilizing user embedding representations generated by a trained neural network. For example, a user embeddings system expands a segment of users by identifying holistically similar users from uniform user embeddings that encode behavior and/or realized traits of the users. Further, the user embeddings system facilitates the expansion of user segments in a particular direction and focus to improve the accuracy of user segments.

Performing automatic segment expansion of user embeddings using multiple user embedding representation types

The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating user embeddings utilizing an LSTM autoencoder model that captures a history of changes to user trait data. For example, the user embeddings system identifies user trait changes from the user trait data over time as well as generates user trait sequences. Further, the user embeddings system can utilize the user trait sequences to train an LSTM neural network in a semi-supervised manner and generate uniform user embeddings for users.

Generating user embedding representations that capture a history of changes to user trait data

Growing community of inventors

San Jose, CA, United States of America

Vijeth Lomada