Google Inc.

Salesforce Com, Inc.

Salesforce, Inc.

Jia Li

Caiming Xiong

Richard Socher

Lichao Sun

Rui Zhang

Chu Hong Hoi

Tomas Jon Pfister

Wenzhuo Yang

Chenxi Li

Harshavardhan Utharavalli

Yongjun Chen

Markus Anderle

Jonathan J Huang

Shengyang Dai

Jonathon Shlens

Yingbo Zhou

Barret Zoph

Kazuma Hashimoto

Wei Hua

Kevin Patrick Murphy

Fei-Fei Li

Jiang Wang

Simo Arajarvi

Zhiwei Liu

Latrice Barnett

Jiyang Gao

Embodiments described herein provides an intent prototypical contrastive learning framework that leverages intent similarities between users with different behavior sequences. Specifically, user behavior sequences are encoded into a plurality of user interest representations. The user interest representations are clustered into a plurality of clusters based on mutual distances among the user interest representations in a representation space. Intention prototypes are determined based on centroids of the clusters. A set of augmented views for user behavior sequences are created and encoded into a set of view representations. A contrastive loss is determined based on the set of augmented views and the plurality of intention prototypes. Model parameters are updated based at least in part on the contrastive loss.

Systems and methods for sequential recommendation

The present disclosure provides systems and methods that include or otherwise leverage an object detection training model for training a machine-learned object detection model. In particular, the training model can obtain first training data and train the machine-learned object detection model using the first training data. The training model can obtain second training data and input the second training data into the machine-learned object detection model, and receive as an output of the machine-learned object detection model, data that describes the location of a detected object of a target category within images from the second training data. The training model can determine mined training data based on the output of the machine-learned object detection model, and train the machine-learned object detection model based on the mined training data.

Noise tolerant ensemble RCNN for semi-supervised object detection

Embodiments described herein provide a two-stage model-agnostic approach for generating counterfactual explanation via counterfactual feature selection and counterfactual feature optimization. Given a query instance, counterfactual feature selection picks a subset of feature columns and values that can potentially change the prediction and then counterfactual feature optimization determines the best feature value for the selected feature as a counterfactual example.

Systems and methods for counterfactual explanation in machine learning models

Embodiments are directed to a machine learning recommendation system. The system receives a user query for generating a recommendation for one or more items with an explanation associated with recommending the one or more items. The system obtains first features of at least one user and second features of a set of items. The system provides the first features and the second features to a first machine learning network for determining a predicted score for an item. The system provides a portion of the first features and a portion of the second features to second machine learning networks for determining explainability scores for an item and generating corresponding explanation narratives. The system provides the recommendation for one or more items and corresponding explanation narratives based on ranking predicted scores and explainability scores for the items.

Diversity and explainability parameters for recommendation accuracy in machine learning recommendation systems

A method includes obtaining a source training dataset that includes a plurality of source training images and obtaining a target training dataset that includes a plurality of target training images. For each source training image, the method includes translating, using the forward generator neural network G, the source training image to a respective translated target image according to current values of forward generator parameters. For each target training image, the method includes translating, using a backward generator neural network F, the target training image to a respective translated source image according to current values of backward generator parameters. The method also includes training the forward generator neural network G jointly with the backward generator neural network F by adjusting the current values of the forward generator parameters and the backward generator parameters to optimize an objective function.

Training image-to-image translation neural networks

A method for evaluating robustness of one or more target neural network models using natural typos. The method includes receiving one or more natural typo generation rules associated with a first task associated with a first input document type, receiving a first target neural network model, and receiving a first document and corresponding its ground truth labels. The method further includes generating one or more natural typos for the first document based on the one or more natural typo generation rules, and providing, to the first target neural network model, a test document generated based on the first document and the one or more natural typos as an input document to generate a first output. A robustness evaluation result of the first target neural network model is generated based on a comparison between the output and the ground truth labels.

Robustness evaluation via natural typos

Systems and methods are provided for near-zero-cost (NZC) query framework or approach for differentially private deep learning. To protect the privacy of training data during learning, the near-zero-cost query framework transfers knowledge from an ensemble of teacher models trained on partitions of the data to a student model. Privacy guarantees may be understood intuitively and expressed rigorously in terms of differential privacy. Other features are also provided.

Near-zero-cost differentially private deep learning with teacher ensembles

Embodiments described herein provide an attentive network framework that models dynamic attributes with item and feature interactions. Specifically, the attentive network framework first encodes basket item sequences and dynamic attribute sequences with time-aware padding and time/month encoding to capture the seasonal patterns (e.g. in app recommendation, outdoor activities apps are more suitable for summer time while indoor activity apps are better for winter). Then the attentive network framework applies time-level attention modules on basket items' sequences and dynamic user attributes' sequences to capture basket items to basket items and attributes to attributes temporal sequential patterns. After that, an intra-basket attentive module is used on items in each basket to capture the correlation information among items.

Systems and methods for next basket recommendation with dynamic attributes modeling

Approaches for private and interpretable machine learning systems include a system for processing a query. The system includes one or more teacher modules for receiving a query and generating a respective output, one or more privacy sanitization modules for privacy sanitizing the respective output of each of the one or more teacher modules, and a student module for receiving a query and the privacy sanitized respective output of each of the one or more teacher modules and generating a result. Each of the one or more teacher modules is trained using a respective private data set. The student module is trained using a public data set. In some embodiments, human understandable interpretations of an output from the student module is provided to a model user.

Data privacy protected machine learning systems

A computer-implemented method for training a forward generator neural network G to translate a source image in a source domain X to a corresponding target image in a target domain Y is described. The method includes: obtaining a source training dataset sampled from the source domain X according to a source domain distribution, the source training dataset comprising a plurality of source training images; obtaining a target training dataset sampled from the target domain Y according to a target domain distribution, the target training dataset comprising a plurality of target training images; for each of the source training images in the source training dataset, translating, using the forward generator neural network G, each source training image to a respective translated target image in the target domain Y according to current values of forward generator parameters of the forward generator neural network G; for each of the target training images in the target training dataset, translating, using a backward generator neural network F, each target training image to a respective translated source image in the source domain X according to current values of backward generator parameters of the backward generator neural network F; and training the forward generator neural network G jointly with the backward generator neural network F by adjusting the current values of the forward generator parameters and the backward generator parameters to optimize an objective function, wherein the objective function comprises a harmonic loss component that ensures (i) similarity-consistency between patches in each source training image and patches in its corresponding translated target image, and (ii) similarity-consistency between patches in each target training image and patches in its corresponding translated source image.

A method for determining an architecture for a task neural network configured to perform a particular machine learning task is described. The method includes obtaining data specifying a current set of candidate architectures for the task neural network; for each candidate architecture in the current set: processing the data specifying the candidate architecture using a performance prediction neural network having multiple performance prediction parameters, the performance prediction neural network being configured to process the data specifying the candidate architecture in accordance with current values of the performance prediction parameters to generate a performance prediction that characterizes how well a neural network having the candidate architecture would perform after being trained on the particular machine learning task; and generating an updated set of candidate architectures by selecting one or more of the candidate architectures in the current set based on the performance predictions for the candidate architectures in the current set.

Growing community of inventors

Mountain View, CA, United States of America

Jia Li