Adobe, Inc.

Tong Yu

Ruiyi Zhang

Sungchul Kim

Subrata Mitra

Eunyee Koh

Handong Zhao

Jiuxiang Gu

Kanak Vivek Mahadik

Rui Wang

Ryan A Rossi

William Brandon George

Wei Zhang

Saayan Mitra

Nedim Lipka

Rajiv Jain

Vlad Ion Morariu

Tung Mai

Tong Sun

Ritwik Sinha

Christopher Alan Tensmeyer

Nikhil Sheoran

Xiang Chen

Shunan Guo

Uttaran Bhattacharya

Said Kobeissi

Victor Soares Bursztyn

Jordan Walker

Manas Garg

Prithvi Bhutani

Shaddy Garg

Yash Gadhia

Arjun Kashettiwar

Anjali Yadav

Yufan Zhou

Junda Wu

Tyler Rasmussen

Samuel Nephi Grigg

Abhisek Trivedi

Zhendong Chu

Alexandru Ionut Hodorogea

Saurabh Tripathy

Embodiments of the present disclosure provide systems, methods, and computer storage media for resource provisioning of microservices using guided order of learning in a reinforcement learning framework. In embodiments, service resource information relating to microservices operating in a computing environment is received and used to perform a similarity analysis to generate similarity scores for each of the services. The service resource information is ordered based on a closeness between the similarity scores of the services. The ordered service resource information is inputted into a reinforcement learning agent to generate a resource configuration determination of at least one service of the services. The resource configuration determination is then provided to a provisioning component associated with the computing environment for provisioning the microservice.

Resource provisioning by a reinforcement learning framework using guided ordering of services

This disclosure describes one or more implementations of systems, non-transitory computer-readable media, and methods that train a named entity recognition (NER) model with noisy training data through a self-cleaning discriminator model. For example, the disclosed systems utilize a self-cleaning guided denoising framework to improve NER learning on noisy training data via a guidance training set. In one or more implementations, the disclosed systems utilize, within the denoising framework, an auxiliary discriminator model to correct noise in the noisy training data while training an NER model through the noisy training data. For example, while training the NER model to predict labels from the noisy training data, the disclosed systems utilize a discriminator model to detect noisy NER labels and reweight the noisy NER labels provided for training in the NER model.

Generating an improved named entity recognition model using noisy data with a self-cleaning discriminator model

A method, apparatus, non-transitory computer readable medium, and system for document retrieval include obtaining a query and a document. A prompt generator generates a prompt for a reasoning model based on the query and the document. The reasoning model generates a reasoning result based on the prompt. In some cases, the reasoning result indicates that the document answers the query. A machine learning model provides the document in response to the query based on the reasoning result.

In-context and semantic-aware ensemble model for document retrieval

Embodiments of the technology described herein describe a machine classifier capable of continually learning new classes through a continual few-shot learning approach. A natural language processing (NLP) machine classifier may initially be trained to identify a plurality of other classes through a conventional training process. In order to learn a new class, natural-language training data for a new class is generated. The training data for the new class may be few-shot training data. The training also uses synthetic training data that represents each of the plurality of other classes. The synthetic training data may be generated through a model inversion of the original classifier. The synthetic training data and the natural-language training data are used to retrain the NLP classifier to identify text in the plurality of other classes and the new class using.

Teaching a machine classifier to recognize a new class

Systems and methods that enable the efficient and adaptive allocation of resources dedicated to a virtualized resource-based computation (e.g., one or more information processing tasks) are provided. In one embodiment, a reward model is generated based on a set of statistical distributions, for example, in response to receiving a request to launch a set of VCRs. Thereafter, an expected reward is predicting for each configuration of a set of configurations based on the reward model and one or more parameters of the corresponding configuration. The expected reward indicates an efficiency in distribution or allocation of physical computation resources to the set of VCRs. A configuration of the set of configurations is selected based on the predicted expected reward for the configuration. The set of VCRs are then configured with the selected configuration.

Efficient adaptive allocation of resources for computational systems via statistically derived linear models

Methods for determining optimal cloud service resource include determining a reward function for a set of resource configurations identifying cloud service resource parameters. The cloud service resource parameters include a source parameter and a target parameter of services to provide a client computing device. A source parameter dataset for the source parameter and a target parameter dataset is generated using the reward function and historical source parameter data. The matrices are then subject to SVD and clustering. A target parameter reward dataset is learned from output of the SVD and clustering. The target parameter dataset is used to determine the parameters for the target parameter for providing corresponding cloud service resources.

Transferable clustering of contextual bandits for cloud service resource allocation

Graphic visualizations, such as charts or graphs conveying data attribute values, can be generated based on natural language queries, i.e., natural language requests. To do so, a natural language request is parsed into n-grams, and from the n-grams, word embeddings are determined using a natural language model. Data attributes for the graphic visualization are discovered in the vector space from the word embeddings. The type of graphic visualization can be determined based on a request intent, which is determined using a trained intent classifier. The graphic visualization is generated to include the data attribute values of the discovered data attributes, and in accordance with the graphic visualization type.

Learning-based method for generating visualizations via natural language

The present disclosure relates to systems, non-transitory computer-readable media, and methods that implement a neural network framework for interactive multi-round image generation from natural language inputs. Specifically, the disclosed systems provide an intelligent framework (i.e., a text-based interactive image generation model) that facilitates a multi-round image generation and editing workflow that comports with arbitrary input text and synchronous interaction. In particular embodiments, the disclosed systems utilize natural language feedback for conditioning a generative neural network that performs text-to-image generation and text-guided image modification. For example, the disclosed systems utilize a trained model to inject textual features from natural language feedback into a unified joint embedding space for generating text-informed style vectors. In turn, the disclosed systems can generate an image with semantically meaningful features that map to the natural language feedback. Moreover, the disclosed systems can persist these semantically meaningful features throughout a refinement process and across generated images.

Utilizing a generative neural network to interactively create and modify digital images based on natural language feedback

Some techniques described herein relate to utilizing a machine-learning (ML) model to select respective samples for queries of a query sequence. In one example, a method includes receiving a query in a query sequence, where the query is directed toward a dataset. Samples are available as down-sampled versions of the dataset. The method further include applying an agent to select, for the query, a sample from among the samples of the dataset. The agent includes an ML model trained, such as via intent-based reinforcement learning, to select respective samples for queries. The query is then executed against the sample to output a response.

Intent-aware learning for automated sample selection in interactive data exploration

Growing community of inventors

San Jose, CA, United States of America

Tong Yu